Professor, University of Texas, Austin
4 papers at NeurIPS 2025
We provide a wide range of nearly optimal guarantees for several fundamental problems in robust supervised learning based on a single iterative polynomial filtering algorithm.
Training protein generative model with noisy synthetic structures
We give a polynomial time algorithm for learning $O(log n)$-juntas over smoothed Markov Random fields
We improve the quality of generative models by using low-quality, corrupted, and out-of-distribution data
