mixing time

Fast Conditional Mixing of MCMC Algorithms for Non-log-concave Distributions NeurIPS 2023 Resolving the Mixing Time of the Langevin Algorithm to its Stationary Distribution for Log-Concave Sampling COLT 2023 Sampling random graph homomorphisms and applications to network data analysis JMLR 2023 Adapting to Mixing Time in Stochastic Optimization with Markovian Data ICML 2022 An Efficient Sampling Algorithm for Non-smooth Composite Potentials JMLR 2022 Continual Learning In Environments With Polynomial Mixing Times NeurIPS 2022 Fast Mixing of Stochastic Gradient Descent with Normalization and Weight Decay NeurIPS 2022 Learning with little mixing NeurIPS 2022 Minimax Mixing Time of the Metropolis-Adjusted Langevin Algorithm for Log-Concave Sampling JMLR 2022 Non-asymptotic and Accurate Learning of Nonlinear Dynamical Systems JMLR 2022 Optimal and instance-dependent guarantees for Markovian linear stochastic approximation COLT 2022 Rapidly Mixing Multiple-try Metropolis Algorithms for Model Selection Problems NeurIPS 2022 Sqrt(d) Dimension Dependence of Langevin Monte Carlo ICLR 2022 Three-stage Evolution and Fast Equilibrium for SGD with Non-degerate Critical Points ICML 2022 Fast Doubly-Adaptive MCMC to Estimate the Gibbs Partition Function with Weak Mixing Time Bounds NeurIPS 2021 High-Order Langevin Diffusion Yields an Accelerated MCMC Algorithm JMLR 2021 Lower Bounds on Metropolized Sampling Methods for Well-Conditioned Distributions NeurIPS 2021 Mixing Time of Metropolis-Hastings for Bayesian Community Detection JMLR 2021 Optimal dimension dependence of the Metropolis-Adjusted Langevin Algorithm COLT 2021 Structured Logconcave Sampling with a Restricted Gaussian Oracle COLT 2021 Towards Tight Bounds on the Sample Complexity of Average-reward MDPs ICML 2021 Fast mixing of Metropolized Hamiltonian Monte Carlo: Benefits of multi-step gradients JMLR 2020 Langevin Monte Carlo without smoothness AISTATS 2020 Least Squares Regression with Markovian Data: Fundamental Limits and Algorithms NeurIPS 2020 Logsmooth Gradient Concentration and Tighter Runtimes for Metropolized Hamiltonian Monte Carlo COLT 2020