Skip to contentSkip to filters

We use cookies for analytics.

Inference-Time Algorithms: A Theoretical Lens on Tractability and Error Propagation

Andrej Risteski

Carnegie Mellon University

Recording

47 min

Abstract

Inference-time algorithms place pretrained models inside larger computational loops, trading extra computation for accuracy or control. This talk studies efficiency and error propagation with imperfect learned oracles. Examples include stochastic backtracking in generator–verifier systems and the conditions under which diffusion steering can favour rewards while remaining close to the original model.

Topics