learning-theory

This paper proposes using pairwise queries to improve selective classification for binary classification, particularly where confidence estimates are inconsistent, as in LLM in-context learning. Theoretical conditions and experiments on synthetic and real datasets show that pairwise query-based algorithms achieve better accuracy-cost tradeoffs than raw confidence estimates.

This paper proposes a unified theoretical framework for phase transitions in deep learning (grokking, emergent capabilities) and non-equilibrium chemistry, describing both as driven informational systems governed by two gradient fields.

This paper provides the first non-asymptotic sample complexity bounds for learning exponential families of polynomials with score matching, showing polynomial dependence on model dimension.