Differences
This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision | |||
| klderivation [2024/12/24 12:57] – [Connecting to the free energy objective] pedroortega | klderivation [2024/12/24 12:58] (current) – [Connecting to the free energy objective] pedroortega | ||
|---|---|---|---|
| Line 88: | Line 88: | ||
| We can transform the above equality into a variational principle by replacing the individual choice costs $C(x \cap d|x \cap c)$ with arbitrary numbers. The resulting expression is convex in the posterior choice probabilities $P(x|d)$, so we get a nice and clean objective function with a unique minimum. | We can transform the above equality into a variational principle by replacing the individual choice costs $C(x \cap d|x \cap c)$ with arbitrary numbers. The resulting expression is convex in the posterior choice probabilities $P(x|d)$, so we get a nice and clean objective function with a unique minimum. | ||
| - | We can even go a step further: noticing that the variational problem is translationally invariant in the costs, and multiplying the expression by $-1$, we can treat the costs as utilities, obtaining | + | We can even go a step further: noticing that the variational problem is translationally invariant in the costs, and multiplying the expression by $-1$, we can treat the resulting " |
| \[ | \[ | ||
| \sum_x P(x|d) U(x) - \frac{1}{\beta} \sum_x P(x|d) \log \frac{ P(x|d) }{ P(x|c) }. | \sum_x P(x|d) U(x) - \frac{1}{\beta} \sum_x P(x|d) \log \frac{ P(x|d) }{ P(x|c) }. | ||