Alain Durmus

Divide-and-Conquer Posterior Sampling for Denoising Diffusion priors NeurIPS 2024 Implicit Bias in Noisy-SGD: With Applications to Differentially Private Training AISTATS 2024 Learning to Mitigate Externalities: the Coase Theorem with Hindsight Rationality NeurIPS 2024 Piecewise deterministic generative models NeurIPS 2024 Shape analysis for time series NeurIPS 2024 Stochastic Approximation with Biased MCMC for Expectation Maximization AISTATS 2024 Theoretical guarantees in KL for Diffusion Flow Matching NeurIPS 2024 Unravelling in Collaborative Learning NeurIPS 2024 Watermarking Makes Language Models Radioactive NeurIPS 2024 Approximate Heavy Tails in Offline (Multi-Pass) Stochastic Gradient Descent NeurIPS 2023 Federated Averaging Langevin Dynamics: Toward a unified theory and new algorithms AISTATS 2023 Non-asymptotic convergence bounds for Sinkhorn iterates and their gradients: a coupling approach. COLT 2023 Tight Regret and Complexity Bounds for Thompson Sampling via Langevin Monte Carlo AISTATS 2023 Tree-Based Diffusion Schrödinger Bridge with Applications to Wasserstein Barycenters NeurIPS 2023 Unbiased constrained sampling with Self-Concordant Barrier Hamiltonian Monte Carlo NeurIPS 2023 FedPop: A Bayesian Approach for Personalised Federated Learning NeurIPS 2022 Local-Global MCMC kernels: the best of both worlds NeurIPS 2022 QLSD: Quantised Langevin Stochastic Dynamics for Bayesian Federated Learning AISTATS 2022 Convergence rates and approximation results for SGD and its continuous-time counterpart COLT 2021 DG-LMC: A Turn-key and Scalable Synchronous Distributed MCMC Algorithm via Langevin Monte Carlo within Gibbs ICML 2021 Fast Approximation of the Sliced-Wasserstein Distance Using Concentration of Random Projections NeurIPS 2021 Monte Carlo Variational Auto-Encoders ICML 2021 NEO: Non Equilibrium Sampling on the Orbits of a Deterministic Transform NeurIPS 2021 On Riemannian Stochastic Approximation Schemes with Fixed Step-Size AISTATS 2021 On the Stability of Random Matrix Product with Markovian Noise: Application to Linear Stochastic Approximation and TD Learning COLT 2021 Tight High Probability Bounds for Linear Stochastic Approximation with Fixed Stepsize NeurIPS 2021 Quantitative Propagation of Chaos for SGD in Wide Neural Networks NeurIPS 2020 Statistical and Topological Properties of Sliced Probability Divergences NeurIPS 2020 Analysis of Langevin Monte Carlo via Convex Optimization JMLR 2019 Asymptotic Guarantees for Learning Generative Models with the Sliced-Wasserstein Distance NeurIPS 2019 Copula-like Variational Inference NeurIPS 2019 Sliced-Wasserstein Flows: Nonparametric Generative Modeling via Optimal Transport and Diffusions ICML 2019 The promises and pitfalls of Stochastic Gradient Langevin Dynamics NeurIPS 2018 Sampling from a log-concave distribution with compact support with proximal Langevin Monte Carlo COLT 2017 Stochastic Gradient Richardson-Romberg Markov Chain Monte Carlo NeurIPS 2016