51 citations · 116 across the 31 of their papers we have counts for
32 papers
Uniform-in-time Propagation-of-Chaos for Stein Variational Gradient Descent
Krishnakumar Balasubramanian, Sayan Banerjee, Anna Korba
We study uniform-in-time propagation-of-chaos for continuous-time Stein Variational Gradient Descent (SVGD). Classical finite-time propagation-of-chaos estimates for mean-field sys…
Highly Data Parallelizable Estimation of the Sliced-Wasserstein Distance Using Cumulative Distribution Functions
Christophe Vauthier, Quentin Mérigot, Anna Korba
The Sliced Wasserstein (SW) distance has emerged as a computationally attractive alternative to the Wasserstein distance by leveraging one-dimensional optimal transport along rando…
A Unifying View of Variational Generative Wasserstein Flows
Paul Caucheteux, Clément Bonet, Anna Korba
Many modern generative models can be viewed as minimizing divergences between probability distributions, yet they rely on different algorithmic and geometric principles. Wasserstei…
How Do Uncertainty Estimators Align with Hallucination Occurrence in LLMs?
Yedidia Agnimo, Anna Korba, Annabelle Blangero +2
Large language models (LLMs) can hallucinate, but do model uncertainty estimators reliably reveal when they do? Although uncertainty estimators are increasingly used to identify un…
Generalized Discrete Diffusion from Snapshots
Oussama Zekri, Théo Uscidda, Nicolas Boullé +1
We introduce Generalized Discrete Diffusion from Snapshots (GDDS), a unified framework for discrete diffusion modeling that supports arbitrary noising processes over large discrete…
A Computable Measure of Suboptimality for Entropy-Regularised Variational Objectives
Clémentine Chazal, Heishiro Kanagawa, Zheyang Shen +2
Several methods in statistics and machine learning target a probability distribution for which an entropy-regularised variational objective is minimised. This increased flexibility…
Flowing Datasets with Wasserstein over Wasserstein Gradient Flows
Clément Bonet, Christophe Vauthier, Anna Korba
Many applications in machine learning involve data represented as probability distributions. The emergence of such data requires radically novel techniques to design tractable grad…
Variational Inference with Mixtures of Isotropic Gaussians
Marguerite Petit-Talamon, Marc Lambert, Anna Korba
Variational inference (VI) is a popular approach in Bayesian inference, that looks for the best approximation of the posterior distribution within a parametric family, minimizing a…
DDEQs: Distributional Deep Equilibrium Models through Wasserstein Gradient Flows
Jonathan Geuter, Clément Bonet, Anna Korba +1
Deep Equilibrium Models (DEQs) are a class of implicit neural networks that solve for a fixed point of a neural network in their forward pass. Traditionally, DEQs take sequences as…
Towards Understanding Gradient Dynamics of the Sliced-Wasserstein Distance via Critical Point Analysis
Christophe Vauthier, Anna Korba, Quentin Mérigot
In this paper, we investigate the properties of the Sliced Wasserstein Distance (SW) when employed as an objective functional. The SW metric has gained significant interest in the…
Density Ratio Estimation with Conditional Probability Paths
Hanlin Yu, Arto Klami, Aapo Hyvärinen +2
Density ratio estimation in high dimensions can be reframed as integrating a certain quantity, the time score, over probability paths which interpolate between the two densities. I…
Sampling from multi-modal distributions with polynomial query complexity in fixed dimension via reverse diffusion
Adrien Vacher, Omar Chehab, Anna Korba
Even in low dimensions, sampling from multi-modal distributions is challenging. We provide the first sampling algorithm for a broad class of distributions -- including all Gaussian…
Constrained Sampling with Primal-Dual Langevin Monte Carlo
Luiz F. O. Chamon, Mohammad Reza Karimi, Anna Korba
This work considers the problem of sampling from a probability distribution known up to a normalization constant while satisfying a set of statistical constraints specified by the…
Provable Convergence and Limitations of Geometric Tempering for Langevin Dynamics
Omar Chehab, Anna Korba, Austin Stromme +1
Geometric tempering is a popular approach to sampling from challenging multi-modal probability distributions by instead sampling from a sequence of distributions which interpolate,…
(De)-regularized Maximum Mean Discrepancy Gradient Flow
Zonghao Chen, Aratrika Mustafi, Pierre Glaser +3
We introduce a (de)-regularization of the Maximum Mean Discrepancy (DrMMD) and its Wasserstein gradient flow. Existing gradient flows that transport samples from source distributio…
Statistical and Geometrical properties of regularized Kernel Kullback-Leibler divergence
Clémentine Chazal, Anna Korba, Francis Bach
In this paper, we study the statistical and geometrical properties of the Kullback-Leibler divergence with kernel covariance operators (KKL) introduced by Bach [2022]. Unlike the c…
A Practical Diffusion Path for Sampling
Omar Chehab, Anna Korba
Diffusion models are state-of-the-art methods in generative modeling when samples from a target probability distribution are available, and can be efficiently sampled, using score…
Theoretical Guarantees for Variational Inference with Fixed-Variance Mixture of Gaussians
Tom Huix, Anna Korba, Alain Durmus +1
Variational inference (VI) is a popular approach in Bayesian inference, that looks for the best approximation of the posterior distribution within a parametric family, minimizing a…
Unified PAC-Bayesian Study of Pessimism for Offline Policy Learning with Regularized Importance Sampling
Imad Aouali, Victor-Emmanuel Brunel, David Rohde +1
Off-policy learning (OPL) often involves minimizing a risk estimator based on importance weighting to correct bias from the logging policy used to collect data. However, this metho…
Mirror and Preconditioned Gradient Descent in Wasserstein Space
Clément Bonet, Théo Uscidda, Adam David +2
As the problem of minimizing functionals on the Wasserstein space encompasses many applications in machine learning, different optimization algorithms on have receiv…
Bayesian Off-Policy Evaluation and Learning for Large Action Spaces
Imad Aouali, Victor-Emmanuel Brunel, David Rohde +1
In interactive systems, actions are often correlated, presenting an opportunity for more sample-efficient off-policy evaluation (OPE) and learning (OPL) in large action spaces. We…
Implicit Diffusion: Efficient Optimization through Stochastic Sampling
Pierre Marion, Anna Korba, Peter Bartlett +6
We present a new algorithm to optimize distributions defined implicitly by parameterized stochastic diffusions. Doing so allows us to modify the outcome distribution of sampling pr…
Exponential Smoothing for Off-Policy Learning
Imad Aouali, Victor-Emmanuel Brunel, David Rohde +1
Off-policy learning (OPL) aims at finding improved policies from logged bandit data, often by minimizing the inverse propensity scoring (IPS) estimator of the risk. In this work, w…
Sampling with Mollified Interaction Energy Descent
Lingxiao Li, Qiang Liu, Anna Korba +2
Sampling from a target measure whose density is only known up to a normalization constant is a fundamental problem in computational statistics and machine learning. In this paper,…