{"total":227,"rows":[{"id":"2209.11215","title":"Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions","created":"2022-09-22","cited_by_count":445,"area":"diffusion"},{"id":"2308.03686","title":"Nearly $d$-Linear Convergence Bounds for Diffusion Models via Stochastic Localization","created":"2023-08-07","cited_by_count":235,"area":"diffusion"},{"id":"2211.01916","title":"Improved Analysis of Score-based Generative Modeling: User-Friendly Bounds under Minimal Smoothness Assumptions","created":"2022-11-03","cited_by_count":219,"area":"diffusion"},{"id":"2206.06227","title":"Convergence for score-based generative modeling with polynomial complexity","created":"2022-06-13","cited_by_count":177,"area":"diffusion"},{"id":"2305.13122","title":"Policy Representation via Diffusion Probability Model for Reinforcement Learning","created":"2023-05-22","cited_by_count":112,"area":"diffusion"},{"id":"2405.18782","title":"Principled Probabilistic Imaging using Diffusion Models as Plug-and-Play Priors","created":"2024-05-29","cited_by_count":97,"area":"diffusion"},{"id":"2205.15902","title":"Variational inference via Wasserstein gradient flows","created":"2022-05-31","cited_by_count":85,"area":null},{"id":"2303.03384","title":"Restoration-Degradation Beyond Linear Diffusions: A Non-Asymptotic Analysis For DDIM-Type Samplers","created":"2023-03-06","cited_by_count":74,"area":"diffusion"},{"id":"2102.05855","title":"Differential Privacy Dynamics of Langevin Diffusion and Noisy Gradient Descent","created":"2021-02-11","cited_by_count":73,"area":null},{"id":"2202.06386","title":"Improved analysis for a proximal algorithm for sampling","created":"2022-02-13","cited_by_count":73,"area":null},{"id":"2210.00726","title":"Statistical Efficiency of Score Matching: The View from Isoperimetry","created":"2022-10-03","cited_by_count":64,"area":null},{"id":"2202.05214","title":"Towards a Theory of Non-Log-Concave Sampling: First-Order Stationarity Guarantees for Langevin Monte Carlo","created":"2022-02-10","cited_by_count":63,"area":null},{"id":"2205.13710","title":"Privacy of Noisy Stochastic Gradient Descent: More Iterations without More Privacy Loss","created":"2022-05-27","cited_by_count":61,"area":null},{"id":"2210.08911","title":"Forget Unlearning: Towards True Data-Deletion in Machine Learning","created":"2022-10-17","cited_by_count":61,"area":"safety"},{"id":"2402.07747","title":"Optimal score estimation via empirical Bayes smoothing","created":"2024-02-12","cited_by_count":61,"area":null},{"id":"2201.10469","title":"Convex Analysis of the Mean Field Langevin Dynamics","created":"2022-01-25","cited_by_count":55,"area":null},{"id":"2112.15383","title":"Separation of Scales and a Thermodynamic Description of Feature Learning in Some CNNs","created":"2021-12-31","cited_by_count":53,"area":null},{"id":"2310.10835","title":"Provable Probabilistic Imaging using Score-Based Generative Priors","created":"2023-10-16","cited_by_count":51,"area":null},{"id":"2401.10371","title":"Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning","created":"2024-01-18","cited_by_count":49,"area":"safety"},{"id":"2203.05363","title":"Differentially Private Learning Needs Hidden State (Or Much Faster Convergence)","created":"2022-03-10","cited_by_count":48,"area":null},{"id":"2302.10249","title":"Faster high-accuracy log-concave sampling via algorithmic warm starts","created":"2023-02-20","cited_by_count":45,"area":null},{"id":"2307.02037","title":"Reverse Diffusion Monte Carlo","created":"2023-07-05","cited_by_count":41,"area":null},{"id":"2109.12077","title":"The Mirror Langevin Algorithm Converges with Vanishing Bias","created":"2021-09-24","cited_by_count":37,"area":null},{"id":"2303.03589","title":"Towards a Complete Analysis of Langevin Monte Carlo: Beyond Poincar\\'e Inequality","created":"2023-03-07","cited_by_count":31,"area":null},{"id":"2501.05370","title":"Accelerated Diffusion Models via Speculative Sampling","created":"2025-01-09","cited_by_count":31,"area":"diffusion"},{"id":"2211.00450","title":"Birth-death dynamics for sampling: Global convergence, approximations and their asymptotics","created":"2022-11-01","cited_by_count":30,"area":null},{"id":"2302.10081","title":"Improved dimension dependence of a proximal algorithm for sampling","created":"2023-02-20","cited_by_count":30,"area":null},{"id":"2302.08049","title":"Improved Discretization Analysis for Underdamped Langevin Monte Carlo","created":"2023-02-16","cited_by_count":28,"area":null},{"id":"2406.08431","title":"Diffusion Soup: Model Merging for Text-to-Image Diffusion Models","created":"2024-06-12","cited_by_count":26,"area":"diffusion"},{"id":"2109.03839","title":"Sqrt(d) Dimension Dependence of Langevin Monte Carlo","created":"2021-09-08","cited_by_count":25,"area":null},{"id":"2204.10818","title":"Convergence of the Riemannian Langevin Algorithm","created":"2022-04-22","cited_by_count":25,"area":null},{"id":"2305.14164","title":"Improved Convergence of Score-Based Diffusion Models via Prediction-Correction","created":"2023-05-23","cited_by_count":24,"area":"diffusion"},{"id":"2402.05468","title":"Implicit Diffusion: Efficient Optimization through Stochastic Sampling","created":"2024-02-08","cited_by_count":24,"area":null},{"id":"2403.18920","title":"CPR: Retrieval Augmented Generation for Copyright Protection","created":"2024-03-27","cited_by_count":24,"area":"rag"},{"id":"2407.16936","title":"Provable Benefit of Annealed Langevin Monte Carlo for Non-log-concave Sampling","created":"2024-07-24","cited_by_count":23,"area":null},{"id":"2202.13975","title":"A Proximal Algorithm for Sampling","created":"2022-02-28","cited_by_count":22,"area":null},{"id":"2206.11254","title":"Langevin Monte Carlo for Contextual Bandits","created":"2022-06-22","cited_by_count":22,"area":null},{"id":"2210.08448","title":"Resolving the Mixing Time of the Langevin Algorithm to its Stationary Distribution for Log-Concave Sampling","created":"2022-10-16","cited_by_count":22,"area":null},{"id":"2106.03076","title":"A Convergence Theory for SVGD in the Population Limit under Talagrand's Inequality T1","created":"2021-06-06","cited_by_count":21,"area":null},{"id":"2402.03008","title":"Diffusive Gibbs Sampling","created":"2024-02-05","cited_by_count":21,"area":null},{"id":"2410.12456","title":"Training Neural Samplers with Reverse Diffusive KL Divergence","created":"2024-10-16","cited_by_count":21,"area":null},{"id":"2211.13954","title":"Particle-based Variational Inference with Preconditioned Functional Gradient Flow","created":"2022-11-25","cited_by_count":20,"area":null},{"id":"2306.07221","title":"Convergence of mean-field Langevin dynamics: Time and space discretization, stochastic gradient, and variance reduction","created":"2023-06-12","cited_by_count":20,"area":null},{"id":"2310.03597","title":"Sampling via Gradient Flows in the Space of Probability Measures","created":"2023-10-05","cited_by_count":20,"area":null},{"id":"2510.02305","title":"Diffusion Models and the Manifold Hypothesis: Log-Domain Smoothing is Geometry Adaptive","created":"2025-10-02","cited_by_count":20,"area":"diffusion"},{"id":"2107.10731","title":"Neural Variational Gradient Descent","created":"2021-07-22","cited_by_count":19,"area":null},{"id":"2211.07861","title":"Regularized Stein Variational Gradient Flow","created":"2022-11-15","cited_by_count":19,"area":null},{"id":"2402.17886","title":"Zeroth-Order Sampling Methods for Non-Log-Concave Distributions: Alleviating Metastability by Denoising Diffusion","created":"2024-02-27","cited_by_count":19,"area":"diffusion"},{"id":"2405.01425","title":"In-and-Out: Algorithmic Diffusion for Sampling Convex Bodies","created":"2024-05-02","cited_by_count":19,"area":null},{"id":"2303.13429","title":"Interacting Particle Langevin Algorithm for Maximum Marginal Likelihood Estimation","created":"2023-03-23","cited_by_count":17,"area":null},{"id":"2203.16217","title":"Improved Convergence Rate of Stochastic Gradient Langevin Dynamics with Variance Reduction and its Application to Optimization","created":"2022-03-30","cited_by_count":16,"area":null},{"id":"2206.00508","title":"Convergence of Stein Variational Gradient Descent under a Weaker Smoothness Condition","created":"2022-06-01","cited_by_count":16,"area":null},{"id":"2302.12229","title":"An Explicit Expansion of the Kullback-Leibler Divergence along its Fisher-Rao Gradient Flow","created":"2023-02-23","cited_by_count":16,"area":null},{"id":"2310.11914","title":"A connection between Tempering and Entropic Mirror Descent","created":"2023-10-18","cited_by_count":16,"area":null},{"id":"2304.04724","title":"When does Metropolized Hamiltonian Monte Carlo provably outperform Metropolis-adjusted Langevin algorithm?","created":"2023-04-10","cited_by_count":15,"area":null},{"id":"2403.17105","title":"Certified Machine Unlearning via Noisy Stochastic Gradient Descent","created":"2024-03-25","cited_by_count":14,"area":"safety"},{"id":"2409.08469","title":"Improved Finite-Particle Convergence Rates for Stein Variational Gradient Descent","created":"2024-09-13","cited_by_count":14,"area":null},{"id":"2210.02482","title":"Fisher information lower bounds for sampling","created":"2022-10-05","cited_by_count":12,"area":null},{"id":"2304.02599","title":"Query lower bounds for log-concave sampling","created":"2023-04-05","cited_by_count":12,"area":null},{"id":"2311.01046","title":"Time-Independent Information-Theoretic Generalization Bounds for SGLD","created":"2023-11-02","cited_by_count":12,"area":null},{"id":"2401.09016","title":"Fast parallel sampling under isoperimetry","created":"2024-01-17","cited_by_count":12,"area":null},{"id":"2405.15767","title":"Improved Particle Approximation Error for Mean Field Neural Networks","created":"2024-05-24","cited_by_count":12,"area":null},{"id":"2406.12241","title":"More Efficient Randomized Exploration for Reinforcement Learning via Approximate Sampling","created":"2024-06-18","cited_by_count":12,"area":"deeprl"},{"id":"2411.13462","title":"Sampling and Integration of Logconcave Functions by Algorithmic Diffusion","created":"2024-11-20","cited_by_count":12,"area":null},{"id":"2502.05623","title":"Mixing Time of the Proximal Sampler in Relative Fisher Information via Strong Data Processing Inequality","created":"2025-02-08","cited_by_count":12,"area":null},{"id":"2312.08823","title":"Fast sampling from constrained spaces using the Metropolis-adjusted Mirror Langevin algorithm","created":"2023-12-14","cited_by_count":11,"area":null},{"id":"2410.10699","title":"Fast Convergence of $\\Phi$-Divergence Along the Unadjusted Langevin Algorithm and Proximal Sampler","created":"2024-10-14","cited_by_count":11,"area":null},{"id":"2205.14818","title":"Excess Risk of Two-Layer ReLU Neural Networks in Teacher-Student Settings and its Superiority to Kernel Methods","created":"2022-05-30","cited_by_count":10,"area":"distill"},{"id":"2210.07219","title":"Condition-number-independent convergence rate of Riemannian Hamiltonian Monte Carlo with numerical integrators","created":"2022-10-13","cited_by_count":10,"area":null},{"id":"2306.08494","title":"Langevin Monte Carlo for strongly log-concave distributions: Randomized midpoint revisited","created":"2023-06-14","cited_by_count":10,"area":null},{"id":"2310.01762","title":"Sampling Multimodal Distributions with the Vanilla Score: Benefits of Data-Based Initialization","created":"2023-10-03","cited_by_count":10,"area":null},{"id":"2310.16516","title":"Particle-based Variational Inference with Generalized Wasserstein Gradient Flow","created":"2023-10-25","cited_by_count":10,"area":null},{"id":"2310.20579","title":"Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks","created":"2023-10-31","cited_by_count":10,"area":null},{"id":"2410.09697","title":"Provable Convergence and Limitations of Geometric Tempering for Langevin Dynamics","created":"2024-10-13","cited_by_count":10,"area":null},{"id":"2411.00568","title":"Constrained Sampling with Primal-Dual Langevin Monte Carlo","created":"2024-11-01","cited_by_count":10,"area":null},{"id":"2402.14434","title":"Parallelized Midpoint Randomization for Langevin Monte Carlo","created":"2024-02-22","cited_by_count":9,"area":null},{"id":"2405.04795","title":"Variational Schr\\\"odinger Diffusion Models","created":"2024-05-08","cited_by_count":9,"area":"diffusion"},{"id":"2506.09681","title":"Assessing the Quality of Denoising Diffusion Models in Wasserstein Distance: Noisy Score and Optimal Bounds","created":"2025-06-11","cited_by_count":9,"area":"diffusion"},{"id":"2111.04089","title":"Sampling from Log-Concave Distributions with Infinity-Distance Guarantees","created":"2021-11-07","cited_by_count":8,"area":null},{"id":"2210.06539","title":"Quantum Algorithms for Sampling Log-Concave Distributions and Estimating Normalizing Constants","created":"2022-10-12","cited_by_count":8,"area":null},{"id":"2301.11294","title":"Coin Sampling: Gradient-Based Bayesian Inference without Learning Rates","created":"2023-01-26","cited_by_count":8,"area":null},{"id":"2406.14292","title":"Proximal Interacting Particle Langevin Algorithms","created":"2024-06-20","cited_by_count":8,"area":null},{"id":"2408.11686","title":"Plug-in estimation of Schr\\\"odinger bridges","created":"2024-08-21","cited_by_count":8,"area":null},{"id":"2411.13443","title":"Nonlinear Assimilation via Score-based Sequential Langevin Sampling","created":"2024-11-20","cited_by_count":8,"area":null},{"id":"2206.03792","title":"Utilising the CLT Structure in Stochastic Gradient based Sampling : Improved Analysis and Faster Algorithms","created":"2022-06-08","cited_by_count":7,"area":null},{"id":"2207.02189","title":"Accelerating Hamiltonian Monte Carlo via Chebyshev Integration Time","created":"2022-07-05","cited_by_count":7,"area":null},{"id":"2207.04387","title":"Bregman Proximal Langevin Monte Carlo via Bregman--Moreau Envelopes","created":"2022-07-10","cited_by_count":7,"area":null},{"id":"2304.04095","title":"A Simple Proof of the Mixing of Metropolis-Adjusted Langevin Algorithm under Smoothness and Isoperimetry","created":"2023-04-08","cited_by_count":7,"area":null},{"id":"2304.12770","title":"Controlling Posterior Collapse by an Inverse Lipschitz Constraint on the Decoder Network","created":"2023-04-25","cited_by_count":7,"area":null},{"id":"2311.09003","title":"Taming under isoperimetry","created":"2023-11-15","cited_by_count":7,"area":null},{"id":"2402.07355","title":"Sampling from the Mean-Field Stationary Distribution","created":"2024-02-12","cited_by_count":7,"area":null},{"id":"2405.17693","title":"Tamed Langevin sampling under weaker conditions","created":"2024-05-27","cited_by_count":7,"area":null},{"id":"2407.05790","title":"Kinetic Interacting Particle Langevin Monte Carlo","created":"2024-07-08","cited_by_count":7,"area":null},{"id":"2201.08349","title":"Heavy-tailed Sampling via Transformed Unadjusted Langevin Algorithm","created":"2022-01-20","cited_by_count":6,"area":null},{"id":"2205.14192","title":"Constrained Langevin Algorithms with L-mixing External Random Variables","created":"2022-05-27","cited_by_count":6,"area":null},{"id":"2305.17558","title":"Provably Fast Finite Particle Variants of SVGD via Virtual Particle Stochastic Approximation","created":"2023-05-27","cited_by_count":6,"area":null},{"id":"2405.17068","title":"The Poisson Midpoint Method for Langevin Dynamics: Provably Efficient Discretization for Diffusion Models","created":"2024-05-27","cited_by_count":6,"area":"diffusion"},{"id":"2412.07435","title":"Parallel Simulation for Log-concave Sampling and Score-based Diffusion Models","created":"2024-12-10","cited_by_count":6,"area":"diffusion"},{"id":"2501.15910","title":"The Sample Complexity of Online Reinforcement Learning: A Multi-model Perspective","created":"2025-01-27","cited_by_count":6,"area":"deeprl"},{"id":"2505.21892","title":"Almost Linear Convergence under Minimal Score Assumptions: Quantized Transition Diffusion","created":"2025-05-28","cited_by_count":6,"area":"diffusion"}],"next_cursor":"100"}