Elchanan Mossel

Learning to Sample from Censored Markov Random Fields

2021 · arXiv (Cornell University)

We study learning Censor Markov Random Fields (abbreviated CMRFs). These are Markov Random Fields where some of the nodes are censored (not observed). We present an algorithm for learning high-temperature CMRFs within o(n) transportation distance. …

A Mathematical Model for Curriculum Learning for Parities

2023 · arXiv (Cornell University)

Curriculum learning (CL) - training using samples that are generated and presented in a meaningful order - was introduced in the machine learning context around a decade ago. While CL has been extensively used and …

Errors are robustly tamed in cumulative knowledge processes

2025 · Proceedings of the National Academy of Sciences

As knowledge accumulates in science and society in a distributed fashion, erroneous derivations can be introduced into the corpus of knowledge. Such derivations can compromise the validity of any units of knowledge that rely on …

Bypassing the Noisy Parity Barrier: Learning Higher-Order Markov Random Fields from Dynamics

2025

STOC ’25, Prague, Czechia