kl-divergence

Tag

Cards List
#kl-divergence

Measuring Goodhart’s law

OpenAI Blog · 2022-04-13 Cached

OpenAI research formally analyzes Goodhart's law through best-of-n sampling, providing efficient estimators for measuring how well proxy objectives track true objectives and quantifying optimization effort via KL divergence.

0 favorites 0 likes
← Previous
← Back to home

Submit Feedback