Search Results for author: Anna Korba

Found 28 papers, 13 papers with code

DDEQs: Distributional Deep Equilibrium Models through Wasserstein Gradient Flows

1 code implementation3 Mar 2025 Jonathan Geuter, Clément Bonet, Anna Korba, David Alvarez-Melis

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.

Point Cloud Classification Point Cloud Completion

Density Ratio Estimation with Conditional Probability Paths

no code implementations4 Feb 2025 Hanlin Yu, Arto Klami, Aapo Hyvärinen, Anna Korba, Omar Chehab

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.

Density Ratio Estimation

Polynomial time sampling from log-smooth distributions in fixed dimension under semi-log-concavity of the forward diffusion with application to strongly dissipative distributions

no code implementations31 Dec 2024 Adrien Vacher, Omar Chehab, Anna Korba

Under the assumption that the density to sample from is $L$-log-smooth and that the forward process is semi-log-concave: $-\nabla^2 \log(p_t) \succeq -\beta I_d$ for some $\beta \geq 0$, we prove that our algorithm achieves an expected $\epsilon$ error in $\text{KL}$ divergence in $O(d^7(L+\beta)^2L^{d+2}\epsilon^{-2(d+3)}(d+m_2(\mu))^{2(d+1)})$ time with $m_2(\mu)$ the second order moment of $\mu$.

Constrained Sampling with Primal-Dual Langevin Monte Carlo

1 code implementation1 Nov 2024 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 expected values of general nonlinear functions.

Bayesian Inference counterfactual +1

Provable Convergence and Limitations of Geometric Tempering for Langevin Dynamics

no code implementations13 Oct 2024 Omar Chehab, Anna Korba, Austin Stromme, Adrien Vacher

Geometric tempering is a popular approach to sampling from challenging multi-modal probability distributions by instead sampling from a sequence of distributions which interpolate, using the geometric mean, between an easier proposal distribution and the target distribution.

(De)-regularized Maximum Mean Discrepancy Gradient Flow

1 code implementation23 Sep 2024 Zonghao Chen, Aratrika Mustafi, Pierre Glaser, Anna Korba, Arthur Gretton, Bharath K. Sriperumbudur

We introduce a (de)-regularization of the Maximum Mean Discrepancy (DrMMD) and its Wasserstein gradient flow.

Statistical and Geometrical properties of regularized Kernel Kullback-Leibler divergence

1 code implementation29 Aug 2024 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].

A Practical Diffusion Path for Sampling

no code implementations20 Jun 2024 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 matching to estimate score vectors guiding a Langevin process.

Mirror and Preconditioned Gradient Descent in Wasserstein Space

1 code implementation13 Jun 2024 Clément Bonet, Théo Uscidda, Adam David, Pierre-Cyril Aubin-Frankowski, Anna Korba

As the problem of minimizing functionals on the Wasserstein space encompasses many applications in machine learning, different optimization algorithms on $\mathbb{R}^d$ have received their counterpart analog on the Wasserstein space.

Theoretical Guarantees for Variational Inference with Fixed-Variance Mixture of Gaussians

no code implementations6 Jun 2024 Tom Huix, Anna Korba, Alain Durmus, Eric Moulines

In this view, VI over this specific family can be casted as the minimization of a Mollified relative entropy, i. e. the KL between the convolution (with respect to a Gaussian kernel) of an atomic measure supported on Diracs, and the target distribution.

Bayesian Inference LEMMA +1

Unified PAC-Bayesian Study of Pessimism for Offline Policy Learning with Regularized Importance Sampling

no code implementations5 Jun 2024 Imad Aouali, Victor-Emmanuel Brunel, David Rohde, Anna Korba

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.

Generalization Bounds

Bayesian Off-Policy Evaluation and Learning for Large Action Spaces

no code implementations22 Feb 2024 Imad Aouali, Victor-Emmanuel Brunel, David Rohde, Anna Korba

In this framework, we propose sDM, a generic Bayesian approach for OPE and OPL, grounded in both algorithmic and theoretical foundations.

Computational Efficiency Off-policy evaluation

A connection between Tempering and Entropic Mirror Descent

no code implementations18 Oct 2023 Nicolas Chopin, Francesca R. Crucinio, Anna Korba

We establish that tempering SMC corresponds to entropic mirror descent applied to the reverse Kullback-Leibler (KL) divergence and obtain convergence rates for the tempering iterates.

Exponential Smoothing for Off-Policy Learning

no code implementations25 May 2023 Imad Aouali, Victor-Emmanuel Brunel, David Rohde, Anna Korba

In particular, it is also valid for standard IPS without making the assumption that the importance weights are bounded.

valid

Sampling with Mollified Interaction Energy Descent

2 code implementations24 Oct 2022 Lingxiao Li, Qiang Liu, Anna Korba, Mikhail Yurochkin, Justin Solomon

These energies rely on mollifier functions -- smooth approximations of the Dirac delta originated from PDE theory.

Variational Inference of overparameterized Bayesian Neural Networks: a theoretical and empirical study

1 code implementation8 Jul 2022 Tom Huix, Szymon Majewski, Alain Durmus, Eric Moulines, Anna Korba

This paper studies the Variational Inference (VI) used for training Bayesian Neural Networks (BNN) in the overparameterized regime, i. e., when the number of neurons tends to infinity.

Variational Inference

Mirror Descent with Relative Smoothness in Measure Spaces, with application to Sinkhorn and EM

no code implementations17 Jun 2022 Pierre-Cyril Aubin-Frankowski, Anna Korba, Flavien Léger

We also show that Expectation Maximization (EM) can always formally be written as a mirror descent.

Adaptive Importance Sampling meets Mirror Descent: a Bias-variance tradeoff

no code implementations29 Oct 2021 Anna Korba, François Portier

Adaptive importance sampling is a widely spread Monte Carlo technique that uses a re-weighting strategy to iteratively estimate the so-called target distribution.

Kernel Stein Discrepancy Descent

2 code implementations20 May 2021 Anna Korba, Pierre-Cyril Aubin-Frankowski, Szymon Majewski, Pierre Ablin

We investigate the properties of its Wasserstein gradient flow to approximate a target probability distribution $\pi$ on $\mathbb{R}^d$, known up to a normalization constant.

Proximal Causal Learning with Kernels: Two-Stage Estimation and Moment Restriction

2 code implementations10 May 2021 Afsaneh Mastouri, Yuchen Zhu, Limor Gultchin, Anna Korba, Ricardo Silva, Matt J. Kusner, Arthur Gretton, Krikamol Muandet

In particular, we provide a unifying view of two-stage and moment restriction approaches for solving this problem in a nonlinear setting.

Vocal Bursts Valence Prediction

A Non-Asymptotic Analysis for Stein Variational Gradient Descent

no code implementations NeurIPS 2020 Anna Korba, Adil Salim, Michael Arbel, Giulia Luise, Arthur Gretton

We study the Stein Variational Gradient Descent (SVGD) algorithm, which optimises a set of particles to approximate a target probability distribution $\pi\propto e^{-V}$ on $\mathbb{R}^d$.

LEMMA

The Wasserstein Proximal Gradient Algorithm

no code implementations NeurIPS 2020 Adil Salim, Anna Korba, Giulia Luise

Using techniques from convex optimization and optimal transport, we analyze the FB scheme as a minimization algorithm on the Wasserstein space.

Maximum Mean Discrepancy Gradient Flow

1 code implementation NeurIPS 2019 Michael Arbel, Anna Korba, Adil Salim, Arthur Gretton

We construct a Wasserstein gradient flow of the maximum mean discrepancy (MMD) and study its convergence properties.

Dimensionality Reduction and (Bucket) Ranking: a Mass Transportation Approach

1 code implementation15 Oct 2018 Mastane Achab, Anna Korba, Stephan Clémençon

Whereas most dimensionality reduction techniques (e. g. PCA, ICA, NMF) for multivariate data essentially rely on linear algebra to a certain extent, summarizing ranking data, viewed as realizations of a random permutation $\Sigma$ on a set of items indexed by $i\in \{1,\ldots,\; n\}$, is a great statistical challenge, due to the absence of vector space structure for the set of permutations $\mathfrak{S}_n$.

Dimensionality Reduction

Ranking Median Regression: Learning to Order through Local Consensus

no code implementations31 Oct 2017 Stephan Clémençon, Anna Korba, Eric Sibony

In the probabilistic formulation of the 'Learning to Order' problem we propose, which extends the framework for statistical Kemeny ranking aggregation developped in \citet{CKS17}, this boils down to recovering conditional Kemeny medians of $\Sigma$ given $X$ from i. i. d.

regression

Cannot find the paper you are looking for? You can Submit a new open access paper.