3 papers
cs.LG2025
Feel-Good Thompson Sampling for Contextual Bandits: a Markov Chain Monte Carlo Showdown
Emile Anand, Sarah Liaw
Thompson Sampling (TS) is widely used to address the exploration/exploitation tradeoff in contextual bandits, yet recent theory shows that it does not explore aggressively enough i…
cs.AI2025
FOL-Traces: Verified First-Order Logic Reasoning Traces at Scale
Isabelle Lee, Sarah Liaw, Dani Yogatama
Reasoning in language models is difficult to evaluate: natural-language traces are unverifiable, symbolic datasets are too small, and most benchmarks conflate heuristics with infer…
cs.LG2025
Learning local neighborhoods of non-Gaussian graphical models: A measure transport approach
Sarah Liaw, Rebecca Morrison, Youssef Marzouk +1
Identifying the Markov properties or conditional independencies of a collection of random variables is a fundamental task in statistics for modeling and inference. Existing approac…