From the 1 of 8 linked papers with an AI index.
9 papers
Accelerated Mixing Time of Randomized Hamiltonian Monte Carlo
Siddharth Mitra, Vishwak Srinivasan, Xiuyuan Wang +1
The paper proves that Randomized Hamiltonian Monte Carlo mixes faster for log‑concave distributions, providing exponential KL convergence rates and explicit total integration time…
Two-scale criteria for Poincaré and log-Sobolev inequalities with applications to Markov chain Monte Carlo
Vishwak Srinivasan
Given a collection of distributions and a mixing distribution supported over , we propose new sufficient conditions under which the mixture / joint…
Accelerated Convex Optimization via Hamiltonian Dynamics with Deterministic Integration Time
Xiuyuan Wang, Vishwak Srinivasan, Qiang Fu +3
We develop Hamiltonian dynamics-based algorithms for smooth convex optimization that achieve accelerated rates of convergence. By exploiting contraction of averaged Hamiltonian flo…
The Fast Mixing Mechanism for Differential Privacy
Omri Lev, Moshe Shenfeld, Vishwak Srinivasan +2
Randomized sketching is a central tool for compressing large-scale optimization problems while preserving accuracy. In particular, sketches that are based on structured matrices, s…
Near-Optimal Private Linear Regression via Iterative Hessian Mixing
Omri Lev, Moshe Shenfeld, Vishwak Srinivasan +2
We study differentially private ordinary least squares (DP-OLS) with bounded data via sketching-based mechanisms. While Gaussian sketching approaches have been explored for…
Designing Algorithms for Entropic Optimal Transport from an Optimisation Perspective
Vishwak Srinivasan, Qijia Jiang
In this work, we develop a collection of novel methods for the entropic-regularised optimal transport problem, which are inspired by existing mirror descent interpretations of the…