Skip to contentSkip to filters

We use cookies for analytics.

Iterated Models: Expressive Power, Learning, and Chain of Thought

Nati Srebro

Toyota Technological Institute at Chicago

Recording

54 min

Abstract

Sequence models often apply the same learned function repeatedly to generate successive tokens. The talk examines the computations possible even with simple underlying function classes and compares the samples and computation needed to learn these models from final answers or from complete intermediate reasoning sequences.

Topics