Robuta

https://jmlr.org/papers/v22/20-1205.html Langevin Monte Carlo: random coordinate descent and variance reduction langevin monte carlo random coordinate descent variance reduction https://openreview.net/forum?id=5-2mX9_U5i Sqrt(d) Dimension Dependence of Langevin Monte Carlo | OpenReview This article considers the popular MCMC method of unadjusted Langevin Monte Carlo (LMC) and provides a non-asymptotic analysis of its sampling error in... langevin monte carlo sqrt dimension dependence openreview https://openreview.net/forum?id=kEPAmGivMD Deterministic Langevin Monte Carlo with Normalizing Flows for Bayesian Inference | OpenReview Deterministic Langevin Monte Carlo with Normalizing Flows for Bayesian Inference achieves state of the art performance on many challenging high dimensional... langevin monte carlo normalizing flows bayesian inference deterministic https://arxiv.org/abs/2603.02429 [2603.02429] Dimension-Independent Convergence of Underdamped Langevin Monte Carlo in KL Divergence Abstract page for arXiv paper 2603.02429: Dimension-Independent Convergence of Underdamped Langevin Monte Carlo in KL Divergence langevin monte carlo https://jmlr.org/papers/v25/22-1443.html Penalized Overdamped and Underdamped Langevin Monte Carlo Algorithms for Constrained Sampling langevin monte carlo overdamped underdamped https://arxiv.org/abs/2312.17077 [2312.17077] Projected Langevin Monte Carlo algorithms in non-convex and super-linear setting Abstract page for arXiv paper 2312.17077: Projected Langevin Monte Carlo algorithms in non-convex and super-linear setting https://jmlr.org/papers/v22/21-0307.html Decentralized Stochastic Gradient Langevin Dynamics and Hamiltonian Monte Carlo langevin dynamics decentralized stochastic gradient hamiltonian https://deepai.org/publication/non-asymptotic-analysis-of-langevin-type-monte-carlo-algorithms Non-asymptotic analysis of Langevin-type Monte Carlo algorithms | DeepAI Mar 22, 2023 - 03/22/23 - We study Langevin-type algorithms for sampling from Gibbs distributions such that the potentials are dissipative and their weak gr... asymptotic analysis monte carlo non langevin type https://openreview.net/forum?id=nfIAEJFiBZ Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo |... We present a scalable and effective exploration strategy based on Thompson sampling for reinforcement learning (RL). One of the key shortcomings of existing...