User:IssaRice/Logical induction notation: Difference between revisions

From Machinelearning
No edit summary
No edit summary
Line 30: Line 30:
* <math>T_5(\overline{\mathbb V}) \colon \mathcal S \cup \{1\} \to \mathbb R</math>
* <math>T_5(\overline{\mathbb V}) \colon \mathcal S \cup \{1\} \to \mathbb R</math>


If <math>T = c + \xi_1\phi_1 + \cdots + \xi_k\phi_k</math>, then
If <math>T = c + \xi_1\phi_1 + \cdots + \xi_k\phi_k \in \mathcal{E\!F}_n</math>, then


:<math>\mathbb V(T) = c + \xi_1\mathbb V(\phi_1) + \cdots + \xi_k\mathbb V(\phi_k)</math>
:<math>\mathbb V(T) = c + \xi_1\mathbb V(\phi_1) + \cdots + \xi_k\mathbb V(\phi_k) \in \mathcal{E\!F}_n</math>


and
and


:<math>T(\overline{\mathbb V}) = c(\overline{\mathbb V})+ \xi_1(\overline{\mathbb V})\phi_1 + \cdots + \xi_k(\overline{\mathbb V})\phi_k</math>
:<math>T(\overline{\mathbb V}) = c(\overline{\mathbb V})+ \xi_1(\overline{\mathbb V})\phi_1 + \cdots + \xi_k(\overline{\mathbb V})\phi_k \colon \mathcal S \cup \{1\} \to \mathbb R</math>


and
and


:<math>\mathbb W(T(\overline{\mathbb V})) = c(\overline{\mathbb V})+ \xi_1(\overline{\mathbb V})\mathbb W(\phi_1) + \cdots + \xi_k(\overline{\mathbb V})\mathbb W(\phi_k)</math>
:<math>\mathbb W(T(\overline{\mathbb V})) = c(\overline{\mathbb V})+ \xi_1(\overline{\mathbb V})\mathbb W(\phi_1) + \cdots + \xi_k(\overline{\mathbb V})\mathbb W(\phi_k) \in \mathbb R</math>


==External links==
==External links==

Revision as of 04:35, 3 August 2018

This is in user space because it's not really about machine learning.

Term Notation Type Definition Notes
-combination Function application of an -combination uses square brackets instead of parentheses. Why? As far as I can tell, this is because each coefficient is in so is itself a function. This means we have two senses of "application": we can pick out the specific coefficient we want (square brackets), or we can apply each coefficient to return something (parentheses).
Holdings from against (a -combination)
Trading strategy
Feature or equivalently or equivalently

Example of a 5-strategy given on p. 18 of the paper:

Since the coefficients ( and ) are in , this is an -combination. Let's call this 5-strategy . We can pick out the coefficient for the term like . But since each coefficient is a feature (which is a function), we can also apply each coefficient to some valuation sequence , like this:

Now each coefficient is a real number, so is an -combination. Note that since is a function that takes a sentence or the number and is a valuation sequence (not a sentence or number), there appears to be a type error in writing . What is going on is that we aren't evaluating at ; rather, we are evaluating each coefficient of , to convert the range of from to .

To summarize the types:

  • in other words

If , then

and

and

External links