Towards a Theory of Non-Log-Concave Sampling: First-Order Stationarity Guarantees for Langevin Monte Carlo

10 February 2022

Krishnakumar Balasubramanian

Sinho Chewi

Murat A. Erdogdu

Adil Salim

Matthew Shunshi Zhang

ArXiv PDF HTML

Papers citing "Towards a Theory of Non-Log-Concave Sampling: First-Order Stationarity Guarantees for Langevin Monte Carlo"

49 / 49 papers shown

Title
On the query complexity of sampling from non-log-concave distributions Yuchen He Chihao Zhang 41 0 0 10 Feb 2025
Mixing Time of the Proximal Sampler in Relative Fisher Information via Strong Data Processing Inequality Andre Wibisono 53 1 0 08 Feb 2025
Non-geodesically-convex optimization in the Wasserstein space Hoang Phuc Hau Luu Hanlin Yu Bernardo Williams Petrus Mikkola Marcelo Hartmann Kai Puolamaki Arto Klami 57 2 0 08 Jan 2025
Sampling with Adaptive Variance for Multimodal Distributions Bjorn Engquist Kui Ren Yunan Yang 72 1 0 20 Nov 2024
A phase transition in sampling from Restricted Boltzmann Machines Youngwoo Kwon Qian Qin Guanyang Wang Yuchen Wei 20 0 0 10 Oct 2024
Convergence of Noise-Free Sampling Algorithms with Regularized Wasserstein Proximals Fuqun Han Stanley Osher Wuchen Li 47 1 0 03 Sep 2024
Theoretical Guarantees for Variational Inference with Fixed-Variance Mixture of Gaussians Tom Huix Anna Korba Alain Durmus Eric Moulines 36 7 0 06 Jun 2024
Principled Probabilistic Imaging using Diffusion Models as Plug-and-Play Priors Zihui Wu Yu Sun Yifan Chen Bingliang Zhang Yisong Yue Katherine Bouman DiffM 34 20 0 29 May 2024
Tamed Langevin sampling under weaker conditions Iosif Lytras P. Mertikopoulos 46 2 0 27 May 2024
The Poisson Midpoint Method for Langevin Dynamics: Provably Efficient Discretization for Diffusion Models S. Kandasamy Dheeraj M. Nagaraj DiffM 31 2 0 27 May 2024
A Separation in Heavy-Tailed Sampling: Gaussian vs. Stable Oracles for Proximal Samplers Ye He Alireza Mousavi-Hosseini Krishnakumar Balasubramanian Murat A. Erdogdu 28 0 0 27 May 2024
Taming Score-Based Diffusion Priors for Infinite-Dimensional Nonlinear Inverse Problems Lorenzo Baldassari Ali Siahkoohi Josselin Garnier K. Sølna Maarten V. de Hoop DiffM 39 1 0 24 May 2024
On the Convergence of Differentially-Private Fine-tuning: To Linearly Probe or to Fully Fine-tune? Shuqi Ke Charlie Hou Giulia Fanti Sewoong Oh 41 4 0 29 Feb 2024
Zeroth-Order Sampling Methods for Non-Log-Concave Distributions: Alleviating Metastability by Denoising Diffusion Ye He Kevin Rojas Molei Tao DiffM 38 8 0 27 Feb 2024
Continuous-time Riemannian SGD and SVRG Flows on Wasserstein Probabilistic Space Mingyang Yi Bohan Wang 32 0 0 24 Jan 2024
Kernelized Normalizing Constant Estimation: Bridging Bayesian Quadrature and Bayesian Optimization Xu Cai Jonathan Scarlett 24 0 0 11 Jan 2024
Taming under isoperimetry Iosif Lytras Sotirios Sabanis 32 3 0 15 Nov 2023
Particle-based Variational Inference with Generalized Wasserstein Gradient Flow Ziheng Cheng Shiyue Zhang Longlin Yu Cheng Zhang BDL 32 6 0 25 Oct 2023
Provable Probabilistic Imaging using Score-Based Generative Priors Yu Sun Zihui Wu Yifan Chen Berthy Feng Katherine Bouman DiffM 29 26 0 16 Oct 2023
Fast Conditional Mixing of MCMC Algorithms for Non-log-concave Distributions Xiang Cheng Bohan Wang Junzhe Zhang Yusong Zhu 18 6 0 18 Jun 2023
Langevin Monte Carlo for strongly log-concave distributions: Randomized midpoint revisited Lu Yu Avetik G. Karagulyan A. Dalalyan 13 5 0 14 Jun 2023
Conditionally Strongly Log-Concave Generative Models Florentin Guth Etienne Lempereur Joan Bruna S. Mallat 45 3 0 31 May 2023
Provably Fast Finite Particle Variants of SVGD via Virtual Particle Stochastic Approximation Aniket Das Dheeraj M. Nagaraj 38 7 0 27 May 2023
Non-Log-Concave and Nonsmooth Sampling via Langevin Monte Carlo Algorithms Tim Tsz-Kit Lau Han Liu T. Pock 39 4 0 25 May 2023
Learning Rate Free Sampling in Constrained Domains Louis Sharrock Lester W. Mackey Christopher Nemeth 41 2 0 24 May 2023
Subsampling Error in Stochastic Gradient Langevin Diffusions Kexin Jin Chenguang Liu J. Latz 33 0 0 23 May 2023
Forward-backward Gaussian variational inference via JKO in the Bures-Wasserstein Space Michael Diao Krishnakumar Balasubramanian Sinho Chewi Adil Salim BDL 32 21 0 10 Apr 2023
Query lower bounds for log-concave sampling Sinho Chewi Jaume de Dios Pont Jerry Li Chen Lu Shyam Narayanan 32 8 0 05 Apr 2023
Efficient Sampling of Stochastic Differential Equations with Positive Semi-Definite Models Anant Raj Umut Simsekli Alessandro Rudi DiffM 31 1 0 30 Mar 2023
Towards a Complete Analysis of Langevin Monte Carlo: Beyond Poincaré Inequality Alireza Mousavi-Hosseini Tyler Farghly Ye He Krishnakumar Balasubramanian Murat A. Erdogdu 45 25 0 07 Mar 2023
Convergence Rates for Non-Log-Concave Sampling and Log-Partition Estimation David Holzmüller Francis R. Bach 36 8 0 06 Mar 2023
Mean-Square Analysis of Discretized Itô Diffusions for Heavy-tailed Sampling Ye He Tyler Farghly Krishnakumar Balasubramanian Murat A. Erdogdu 47 4 0 01 Mar 2023
Non-convex sampling for a mixture of locally smooth potentials D. Nguyen 33 0 0 31 Jan 2023
Regularized Stein Variational Gradient Flow Ye He Krishnakumar Balasubramanian Bharath K. Sriperumbudur Jianfeng Lu OT 34 11 0 15 Nov 2022
A Dynamical System View of Langevin-Based Non-Convex Sampling Mohammad Reza Karimi Ya-Ping Hsieh Andreas Krause 40 4 0 25 Oct 2022
Sampling with Mollified Interaction Energy Descent Lingxiao Li Qiang Liu Anna Korba Mikhail Yurochkin Justin Solomon 38 15 0 24 Oct 2022
Resolving the Mixing Time of the Langevin Algorithm to its Stationary Distribution for Log-Concave Sampling Jason M. Altschuler Kunal Talwar 38 24 0 16 Oct 2022
Fisher information lower bounds for sampling Sinho Chewi P. Gerber Holden Lee Chen Lu 49 15 0 05 Oct 2022
How good is your Laplace approximation of the Bayesian posterior? Finite-sample computable error bounds for a variety of useful divergences Mikolaj Kasprzak Ryan Giordano Tamara Broderick 33 4 0 29 Sep 2022
Utilising the CLT Structure in Stochastic Gradient based Sampling : Improved Analysis and Faster Algorithms Aniket Das Dheeraj M. Nagaraj Anant Raj 54 6 0 08 Jun 2022
Federated Learning with a Sampling Algorithm under Isoperimetry Lukang Sun Adil Salim Peter Richtárik FedML 26 7 0 02 Jun 2022
Convergence of Stein Variational Gradient Descent under a Weaker Smoothness Condition Lukang Sun Avetik G. Karagulyan Peter Richtárik 26 19 0 01 Jun 2022
Constrained Langevin Algorithms with L-mixing External Random Variables Yu Zheng Andrew G. Lamperski 30 5 0 27 May 2022
Improved Convergence Rate of Stochastic Gradient Langevin Dynamics with Variance Reduction and its Application to Optimization Yuri Kinoshita Taiji Suzuki 18 16 0 30 Mar 2022
A Proximal Algorithm for Sampling Jiaming Liang Yongxin Chen 27 17 0 28 Feb 2022
Heavy-tailed Sampling via Transformed Unadjusted Langevin Algorithm Ye He Krishnakumar Balasubramanian Murat A. Erdogdu 41 5 0 20 Jan 2022
A Convergence Theory for SVGD in the Population Limit under Talagrand's Inequality T1 Adil Salim Lukang Sun Peter Richtárik 26 20 0 06 Jun 2021
Nonasymptotic analysis of Stochastic Gradient Hamiltonian Monte Carlo under local conditions for nonconvex optimization Ömer Deniz Akyildiz Sotirios Sabanis 46 17 0 13 Feb 2020
Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Łojasiewicz Condition Hamed Karimi J. Nutini Mark W. Schmidt 139 1,199 0 16 Aug 2016