Statistical Learning
First Order Stochastic Optimization with Oblivious Noise
We initiate the study of stochastic optimization with oblivious noise, broadly generalizing the standard heavy-tailed noise setup.
Learning Mixtures of Gaussians Using the DDPM Objective
Recent works have shown that diffusion models can learn essentially any distribution provided one can perform score estimation.
k-Means Clustering with Distance-Based Privacy
In this paper, we initiate the study of Euclidean clustering with Distance-based privacy. Distance-based privacy is motivated by the fact that it is often only needed to protect the privacy of exact, rather than approximate, locations.
A Heavy-Tailed Algebra for Probabilistic Programming
Theorem 2) is optimized (4) to correct the bulk approximation.
Mutual Information Regularized Offline Reinforcement Learning
We show that optimizing this lower bound is equivalent to maximizing the likelihood of a one-step improved policy on the offline dataset. Hence, we constrain the policy improvement direction to lie in the data manifold.