4 papers
When few labeled target data suffice: a theory of semi-supervised domain adaptation via fine-tuning from multiple adaptive starts
Wooseok Ha, Yuansi Chen
Semi-supervised domain adaptation (SSDA) seeks to achieve accurate predictions in a target domain with limited labeled target data by exploiting abundant source and unlabeled targe…
Talagrand's convolution conjecture up to loglog via perturbed reverse heat
Yuansi Chen
We prove that under the heat semigroup on the Boolean hypercube, any nonnegative function exhibits a uniform tail bound that is better than Markov's inequality. Specifical…
Regularized Dikin Walks for Sampling Truncated Logconcave Measures, Mixed Isoperimetry and Beyond Worst-Case Analysis
Minhui Jiang, Yuansi Chen
We study the problem of drawing samples from a logconcave distribution truncated on a polytope, motivated by computational challenges in Bayesian statistical models with indicator…
PolytopeWalk: Sparse MCMC Sampling over Polytopes
Benny Sun, Yuansi Chen
High dimensional sampling is an important computational tool in statistics and other computational disciplines, with applications ranging from Bayesian statistical uncertainty quan…