Translating informal probability statements to formal counterparts - Revision history

https://machinelearning.subwiki.org/w/index.php?action=history&feed=atom&title=Translating_informal_probability_statements_to_formal_counterparts Translating informal probability statements to formal counterparts - Revision history 2026-08-12T11:21:57Z Revision history for this page on the wiki MediaWiki 1.41.2 https://machinelearning.subwiki.org/w/index.php?title=Translating_informal_probability_statements_to_formal_counterparts&diff=2918&oldid=prev IssaRice at 22:18, 3 March 2020 2020-03-03T22:18:03Z

<p></p> <table style="background-color: #fff; color: #202122;" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 22:18, 3 March 2020</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l20">Line 20:</td> <td colspan="2" class="diff-lineno">Line 20:</td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>for example sutton and barto (p. 53) say "At each time step, the reward is a simple number, <math>R_t \in \mathbb R</math>." But in this book, they also write (p. xiii) "We also use a slightly different notation than was used in the first edition. In teaching, we have found that the new notation helps to address some common points of confusion. It emphasizes the difference between random variables, denoted with capital letters, and their instantiations, denoted in lower case. For example, the state, action, and reward at time step <math>t</math> are denoted <math>S_t</math>, <math>A_t</math>, and <math>R_t</math>, while their possible values might be denoted <math>s</math>, <math>a</math>, and <math>r</math>." So which is it?</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>for example sutton and barto (p. 53) say "At each time step, the reward is a simple number, <math>R_t \in \mathbb R</math>." But in this book, they also write (p. xiii) "We also use a slightly different notation than was used in the first edition. In teaching, we have found that the new notation helps to address some common points of confusion. It emphasizes the difference between random variables, denoted with capital letters, and their instantiations, denoted in lower case. For example, the state, action, and reward at time step <math>t</math> are denoted <math>S_t</math>, <math>A_t</math>, and <math>R_t</math>, while their possible values might be denoted <math>s</math>, <math>a</math>, and <math>r</math>." So which is it?</div></td></tr> <tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;"></ins></div></td></tr> <tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">there is a kind of strong psychological pull, i think, to say things like <math>R_t \in \mathbb R</math>, despite formally defining <math>R_t : \Omega \to \mathbb R</math> as a random variable. it is tempting to say that a random variable is a real number whose value is """stochastic""".</ins></div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>[[Category:Probability]]</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>[[Category:Probability]]</div></td></tr> </table>

IssaRice https://machinelearning.subwiki.org/w/index.php?title=Translating_informal_probability_statements_to_formal_counterparts&diff=2917&oldid=prev IssaRice at 22:15, 3 March 2020 2020-03-03T22:15:46Z

<p></p> <table style="background-color: #fff; color: #202122;" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 22:15, 3 March 2020</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l18">Line 18:</td> <td colspan="2" class="diff-lineno">Line 18:</td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>there's also the thing where random variables "feel" like they are actually real numbers. e.g. when we treat observed data points as random variables.</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>there's also the thing where random variables "feel" like they are actually real numbers. e.g. when we treat observed data points as random variables.</div></td></tr> <tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;"></ins></div></td></tr> <tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">for example sutton and barto (p. 53) say "At each time step, the reward is a simple number, <math>R_t \in \mathbb R</math>." But in this book, they also write (p. xiii) "We also use a slightly different notation than was used in the first edition. In teaching, we have found that the new notation helps to address some common points of confusion. It emphasizes the difference between random variables, denoted with capital letters, and their instantiations, denoted in lower case. For example, the state, action, and reward at time step <math>t</math> are denoted <math>S_t</math>, <math>A_t</math>, and <math>R_t</math>, while their possible values might be denoted <math>s</math>, <math>a</math>, and <math>r</math>." So which is it?</ins></div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>[[Category:Probability]]</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>[[Category:Probability]]</div></td></tr> </table>

IssaRice https://machinelearning.subwiki.org/w/index.php?title=Translating_informal_probability_statements_to_formal_counterparts&diff=2916&oldid=prev IssaRice at 22:09, 3 March 2020 2020-03-03T22:09:03Z

<p></p> <table style="background-color: #fff; color: #202122;" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 22:09, 3 March 2020</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l8">Line 8:</td> <td colspan="2" class="diff-lineno">Line 8:</td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>| Let <math>X</math> be a normally distributed random variable. || A random variable is a function <math>X : \Omega \to \mathbf R</math>, but here we have not specified the sample space <math>\Omega</math> ||</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>| Let <math>X</math> be a normally distributed random variable. || A random variable is a function <math>X : \Omega \to \mathbf R</math>, but here we have not specified the sample space <math>\Omega</math> ||</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|-</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|-</div></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>| Let <math>X_1, X_2, X_3, \ldots</math> be i.i.d. || again, we have not specified a sample space. here we have to also assume that the sample space is big enough to contain enough randomness in order to make all of the X_i independent. for example, a sample space of <math>\Omega = \{1,2,3,4,5,6\}</math> has "enough randomness" to represent a single roll of a die, it does not have enough randomness to represent two independent rolls of a die. ||</div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>| Let <math>X_1, X_2, X_3, \ldots</math> be i.i.d. || again, we have not specified a sample space. here we have to also assume that the sample space is big enough to contain enough randomness in order to make all of the X_i independent. for example, a sample space of <math>\Omega = \{1,2,3,4,5,6\}</math> has "enough randomness" to represent a single roll of a die, <ins style="font-weight: bold; text-decoration: none;">but </ins>it does not have enough randomness to represent two independent rolls of a die. ||</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|-</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|-</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>| <math>\mathbf E_{z \sim \mathcal D}[f(z)]</math> || again, here we're giving a random variable <math>z</math> without specifying the sample space, and then we're taking its expected value. the reason why this makes sense is that the expected value does not depend on the sample space, as long as the distribution is the same. ||</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>| <math>\mathbf E_{z \sim \mathcal D}[f(z)]</math> || again, here we're giving a random variable <math>z</math> without specifying the sample space, and then we're taking its expected value. the reason why this makes sense is that the expected value does not depend on the sample space, as long as the distribution is the same. ||</div></td></tr> </table>

IssaRice https://machinelearning.subwiki.org/w/index.php?title=Translating_informal_probability_statements_to_formal_counterparts&diff=2915&oldid=prev IssaRice at 22:08, 3 March 2020 2020-03-03T22:08:24Z

<p></p> <table style="background-color: #fff; color: #202122;" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 22:08, 3 March 2020</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l8">Line 8:</td> <td colspan="2" class="diff-lineno">Line 8:</td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>| Let <math>X</math> be a normally distributed random variable. || A random variable is a function <math>X : \Omega \to \mathbf R</math>, but here we have not specified the sample space <math>\Omega</math> ||</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>| Let <math>X</math> be a normally distributed random variable. || A random variable is a function <math>X : \Omega \to \mathbf R</math>, but here we have not specified the sample space <math>\Omega</math> ||</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|-</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|-</div></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>| Let <math>X_1, X_2, X_3, \ldots</math> be i.i.d. || again, we have not specified a sample space. here we have to also assume that the sample space is big enough to contain enough randomness in order to make all of the X_i independent. ||</div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>| Let <math>X_1, X_2, X_3, \ldots</math> be i.i.d. || again, we have not specified a sample space. here we have to also assume that the sample space is big enough to contain enough randomness in order to make all of the X_i independent<ins style="font-weight: bold; text-decoration: none;">. for example, a sample space of <math>\Omega = \{1,2,3,4,5,6\}</math> has "enough randomness" to represent a single roll of a die, it does not have enough randomness to represent two independent rolls of a die</ins>. ||</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|-</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|-</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>| <math>\mathbf E_{z \sim \mathcal D}[f(z)]</math> || again, here we're giving a random variable <math>z</math> without specifying the sample space, and then we're taking its expected value. the reason why this makes sense is that the expected value does not depend on the sample space, as long as the distribution is the same. ||</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>| <math>\mathbf E_{z \sim \mathcal D}[f(z)]</math> || again, here we're giving a random variable <math>z</math> without specifying the sample space, and then we're taking its expected value. the reason why this makes sense is that the expected value does not depend on the sample space, as long as the distribution is the same. ||</div></td></tr> </table>

IssaRice https://machinelearning.subwiki.org/w/index.php?title=Translating_informal_probability_statements_to_formal_counterparts&diff=2914&oldid=prev IssaRice at 22:06, 3 March 2020 2020-03-03T22:06:59Z

<p></p> <table style="background-color: #fff; color: #202122;" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 22:06, 3 March 2020</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l8">Line 8:</td> <td colspan="2" class="diff-lineno">Line 8:</td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>| Let <math>X</math> be a normally distributed random variable. || A random variable is a function <math>X : \Omega \to \mathbf R</math>, but here we have not specified the sample space <math>\Omega</math> ||</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>| Let <math>X</math> be a normally distributed random variable. || A random variable is a function <math>X : \Omega \to \mathbf R</math>, but here we have not specified the sample space <math>\Omega</math> ||</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|-</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|-</div></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>| Let <math>X_1, X_2, X_3, \ldots</math> be i.i.d. || ||</div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>| Let <math>X_1, X_2, X_3, \ldots</math> be i.i.d. || <ins style="font-weight: bold; text-decoration: none;">again, we have not specified a sample space. here we have to also assume that the sample space is big enough to contain enough randomness in order to make all of the X_i independent. </ins>||</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|-</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|-</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>| <math>\mathbf E_{z \sim \mathcal D}[f(z)]</math> || again, here we're giving a random variable <math>z</math> without specifying the sample space, and then we're taking its expected value. the reason why this makes sense is that the expected value does not depend on the sample space, as long as the distribution is the same. ||</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>| <math>\mathbf E_{z \sim \mathcal D}[f(z)]</math> || again, here we're giving a random variable <math>z</math> without specifying the sample space, and then we're taking its expected value. the reason why this makes sense is that the expected value does not depend on the sample space, as long as the distribution is the same. ||</div></td></tr> </table>

IssaRice https://machinelearning.subwiki.org/w/index.php?title=Translating_informal_probability_statements_to_formal_counterparts&diff=2913&oldid=prev IssaRice at 22:05, 3 March 2020 2020-03-03T22:05:17Z

<p></p> <table style="background-color: #fff; color: #202122;" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 22:05, 3 March 2020</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l10">Line 10:</td> <td colspan="2" class="diff-lineno">Line 10:</td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>| Let <math>X_1, X_2, X_3, \ldots</math> be i.i.d. || ||</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>| Let <math>X_1, X_2, X_3, \ldots</math> be i.i.d. || ||</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|-</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|-</div></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>| <math>\mathbf E_{z \sim \mathcal D}[f(z)]</math> || again, here we're giving a random variable <math>z</math> without specifying the sample space, and then we're taking its expected value. the reason why this makes sense is that the expected value <del style="font-weight: bold; text-decoration: none;">does not </del>does not depend on the sample space, as long as the distribution is the same. ||</div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>| <math>\mathbf E_{z \sim \mathcal D}[f(z)]</math> || again, here we're giving a random variable <math>z</math> without specifying the sample space, and then we're taking its expected value. the reason why this makes sense is that the expected value does not depend on the sample space, as long as the distribution is the same. ||</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|-</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|-</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>| rolling one die, and then another die || the confusion here is that we're supposed to have a sample space, but here it seems like we're modifying the sample space. again the informal-ness comes from the fact that we have not fully specified the sample space. here we can think of starting with one sample space, and then "growing" it, or we could just start with the bigger sample space from the start ||</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>| rolling one die, and then another die || the confusion here is that we're supposed to have a sample space, but here it seems like we're modifying the sample space. again the informal-ness comes from the fact that we have not fully specified the sample space. here we can think of starting with one sample space, and then "growing" it, or we could just start with the bigger sample space from the start ||</div></td></tr> </table>

IssaRice https://machinelearning.subwiki.org/w/index.php?title=Translating_informal_probability_statements_to_formal_counterparts&diff=2912&oldid=prev IssaRice at 22:04, 3 March 2020 2020-03-03T22:04:08Z

<p></p> <table style="background-color: #fff; color: #202122;" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 22:04, 3 March 2020</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l14">Line 14:</td> <td colspan="2" class="diff-lineno">Line 14:</td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>| rolling one die, and then another die || the confusion here is that we're supposed to have a sample space, but here it seems like we're modifying the sample space. again the informal-ness comes from the fact that we have not fully specified the sample space. here we can think of starting with one sample space, and then "growing" it, or we could just start with the bigger sample space from the start ||</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>| rolling one die, and then another die || the confusion here is that we're supposed to have a sample space, but here it seems like we're modifying the sample space. again the informal-ness comes from the fact that we have not fully specified the sample space. here we can think of starting with one sample space, and then "growing" it, or we could just start with the bigger sample space from the start ||</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|-</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|-</div></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>| <math>\mathbb E_\pi</math> in reinforcement learning || this usually isn't defined formally, but it means something like: if we expand out the definition of expected value, then whenever we see the expression <math><del style="font-weight: bold; text-decoration: none;">P</del>(a \mid s)</math>, we can substitute it instead with <math>\pi(a\mid s)</math>. ||</div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>| <math>\mathbb E_\pi</math> in reinforcement learning || this usually isn't defined formally, but it means something like: if we expand out the definition of expected value, then whenever we see the expression <math><ins style="font-weight: bold; text-decoration: none;">\Pr</ins>(<ins style="font-weight: bold; text-decoration: none;">A_t = </ins>a \mid <ins style="font-weight: bold; text-decoration: none;">S_t = </ins>s)</math><ins style="font-weight: bold; text-decoration: none;">, for any t</ins>, we can substitute it instead with <math>\pi(a\mid s)</math>. ||</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|}</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|}</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> </table>

IssaRice https://machinelearning.subwiki.org/w/index.php?title=Translating_informal_probability_statements_to_formal_counterparts&diff=2911&oldid=prev IssaRice at 21:48, 3 March 2020 2020-03-03T21:48:46Z

<p></p> <table style="background-color: #fff; color: #202122;" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 21:48, 3 March 2020</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l13">Line 13:</td> <td colspan="2" class="diff-lineno">Line 13:</td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|-</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|-</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>| rolling one die, and then another die || the confusion here is that we're supposed to have a sample space, but here it seems like we're modifying the sample space. again the informal-ness comes from the fact that we have not fully specified the sample space. here we can think of starting with one sample space, and then "growing" it, or we could just start with the bigger sample space from the start ||</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>| rolling one die, and then another die || the confusion here is that we're supposed to have a sample space, but here it seems like we're modifying the sample space. again the informal-ness comes from the fact that we have not fully specified the sample space. here we can think of starting with one sample space, and then "growing" it, or we could just start with the bigger sample space from the start ||</div></td></tr> <tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">|-</ins></div></td></tr> <tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">| <math>\mathbb E_\pi</math> in reinforcement learning || this usually isn't defined formally, but it means something like: if we expand out the definition of expected value, then whenever we see the expression <math>P(a \mid s)</math>, we can substitute it instead with <math>\pi(a\mid s)</math>. ||</ins></div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|}</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|}</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> </table>

IssaRice https://machinelearning.subwiki.org/w/index.php?title=Translating_informal_probability_statements_to_formal_counterparts&diff=2402&oldid=prev IssaRice at 06:36, 10 August 2019 2019-08-10T06:36:50Z

<p></p> <table style="background-color: #fff; color: #202122;" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 06:36, 10 August 2019</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l16">Line 16:</td> <td colspan="2" class="diff-lineno">Line 16:</td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>there's also the thing where random variables "feel" like they are actually real numbers. e.g. when we treat observed data points as random variables.</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>there's also the thing where random variables "feel" like they are actually real numbers. e.g. when we treat observed data points as random variables.</div></td></tr> <tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;"></ins></div></td></tr> <tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">[[Category:Probability]]</ins></div></td></tr> </table>

IssaRice https://machinelearning.subwiki.org/w/index.php?title=Translating_informal_probability_statements_to_formal_counterparts&diff=2401&oldid=prev IssaRice at 06:34, 10 August 2019 2019-08-10T06:34:13Z

<p></p> <table style="background-color: #fff; color: #202122;" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 06:34, 10 August 2019</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l14">Line 14:</td> <td colspan="2" class="diff-lineno">Line 14:</td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>| rolling one die, and then another die || the confusion here is that we're supposed to have a sample space, but here it seems like we're modifying the sample space. again the informal-ness comes from the fact that we have not fully specified the sample space. here we can think of starting with one sample space, and then "growing" it, or we could just start with the bigger sample space from the start ||</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>| rolling one die, and then another die || the confusion here is that we're supposed to have a sample space, but here it seems like we're modifying the sample space. again the informal-ness comes from the fact that we have not fully specified the sample space. here we can think of starting with one sample space, and then "growing" it, or we could just start with the bigger sample space from the start ||</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|}</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|}</div></td></tr> <tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;"></ins></div></td></tr> <tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">there's also the thing where random variables "feel" like they are actually real numbers. e.g. when we treat observed data points as random variables.</ins></div></td></tr> </table>

IssaRice