DanielFilan

Comments

Belief Functions And Decision Theory

Lets ponder the bestiary of decision-theory problems

"Lets" should be "Let's"

Belief Functions And Decision Theory

Also, after theorem 3.2:

First, they let us freely translate between psuedocausal/acausal and causal/surcausal.

Looks like 'causal' and 'acausal' are swapped here?

Belief Functions And Decision Theory

In definition 20 you have

I'm kind of confused here: what's , and isn't a single action? [EDIT: oops, forgot that was nirvana]

Understanding “Deep Double Descent”

Finally got around to that one, and am also pretty into that explanation for the cases of double descent we observe. It also tentatively makes me want to say that the decrease in variance with model size is the 'real story'/primary thing we should think about.

Basic Inframeasure Theory

A Markov kernel is a function X\to\Delta Y

Missing math formatting

Basic Inframeasure Theory

Lets say we've got an infradistribution h on the space X

Should be "Let's say"

Basic Inframeasure Theory

(and everything we're querying our set B with is a positive functional by Proposition 1,

This open paren seems to me to have no matching close paren.

Basic Inframeasure Theory

For those like me who hadn't heard of the Kantorovich-Rubinstein metric, note that it's the same as the perhaps-familiar Wasserstein metric.

Basic Inframeasure Theory

Typo:

The closed convex cone of sa-measures. An sa-meaure is a pair (m,b)

should be 'an sa-measure' not 'an sa-meaure'.

AXRP Episode 4 - Risks from Learned Optimization with Evan Hubinger

Also my biggest take-away was the argument for why we shouldn't expect myopia by default. But perhaps this was already obvious to others.

Load More