OWOlivier Wintenberger

Olivier Wintenberger

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Olivier Wintenberger has a total of 37 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    High-Probability Minimax Adaptive Estimation in Besov Spaces via Online-to-Batch

    by Paul Liautaud, Pierre Gaillard, Olivier Wintenberger

    We study nonparametric regression over Besov spaces from noisy observations under sub-exponential noise, aiming to achieve minimax-optimal guarantees on the integrated squared error that hold with high probability and adapt to the unknown noise level. To this end, we propose a wavelet-based online learning algorithm that dynamically adjusts to the observed gradient noise by adaptively clipping it at an appropriate level, eliminating the need to tune parameters such as the noise variance or gradient bounds. As a by-product of our analysis, we derive high-probability adaptive regret bounds that scale with the $\ell_1$-norm of the competitor. Finally, in the batch statistical setting, we obtain adaptive and minimax-optimal estimation rates for Besov spaces via a refined online-to-batch conversion. This approach carefully exploits the structure of the squared loss in combination with self-normalized concentration inequalities.

    • 11 February 2026
    • Published by HAL in HAL
    Open Access

    High-Probability Minimax Adaptive Estimation in Besov Spaces via Online-to-Batch

    by Paul Liautaud, Pierre Gaillard, Olivier Wintenberger

    We study nonparametric regression over Besov spaces from noisy observations under sub-exponential noise, aiming to achieve minimax-optimal guarantees on the integrated squared error that hold with high probability and adapt to the unknown noise level. To this end, we propose a wavelet-based online learning algorithm that dynamically adjusts to the observed gradient noise by adaptively clipping it at an appropriate level, eliminating the need to tune parameters such as the noise variance or gradient bounds. As a by-product of our analysis, we derive high-probability adaptive regret bounds that scale with the $\ell_1$-norm of the competitor.Finally, in the batch statistical setting, we obtain adaptive and minimax-optimal estimation rates for Besov spaces via a refined online-to-batch conversion. This approach carefully exploits the structure of the squared loss in combination with self-normalized concentration inequalities.

  • Open Access

    Assessing Extrapolation of Peaks Over Thresholds with Martingale Testing

    by Joseph de Vilmarest, Olivier Wintenberger

    We present the winning strategy for the EVA2025 Data Challenge, which aimed to estimate the probability of extreme precipitation events. These events occurred at most once in the dataset making the challenge fundamentally one of extrapolating extreme values. Given the scarcity of extreme events, we argue that a simple, robust modeling approach is essential. We adopt univariate models instead of multivariate ones and model Peaks Over Thresholds using Extreme Value Theory. Specifically, we fit an exponential distribution to model exceedances of the target variable above a high quantile (after seasonal adjustment). The novelty of our approach lies in using martingale testing to evaluate the extrapolation power of the procedure and to agnostically select the level of the high quantile. While this method has several limitations, we believe that framing extrapolation as a game opens the door to other agnostic approaches in Extreme Value Analysis.

    • 1 December 2025
    • Published by HAL in HAL
    Open Access

    Assessing Extrapolation of Peaks Over Thresholds with Martingale Testing

    by Joseph De Vilmarest, Olivier Wintenberger

    We present the winning strategy for the EVA2025 Data Challenge, which aimed to estimate the probability of extreme precipitation events. These events occurred at most once in the dataset making the challenge fundamentally one of extrapolating extreme values. Given the scarcity of extreme events, we argue that a simple, robust modeling approach is essential. We adopt univariate models instead of multivariate ones and model Peaks Over Thresholds using Extreme Value Theory. Specifically, we fit an exponential distribution to model exceedances of the target variable above a high quantile (after seasonal adjustment). The novelty of our approach lies in using martingale testing to evaluate the extrapolation power of the procedure and to agnostically select the level of the high quantile. While this method has several limitations, we believe that framing extrapolation as a game opens the door to other agnostic approaches in Extreme Value Analysis.

  • Open Access

    Decreasing Entropic Regularization Averaged Gradient for Semi-Discrete Optimal Transport

    by Ferdinand Genans, Antoine Godichon-Baggioni, François-Xavier Vialard, Olivier Wintenberger

    Adding entropic regularization to Optimal Transport (OT) problems has become a standard approach for designing efficient and scalable solvers. However, regularization introduces a bias from the true solution. To mitigate this bias while still benefiting from the acceleration provided by regularization, a natural solver would adaptively decrease the regularization as it approaches the solution. Although some algorithms heuristically implement this idea, their theoretical guarantees and the extent of their acceleration compared to using a fixed regularization remain largely open. In the setting of semi-discrete OT, where the source measure is continuous and the target is discrete, we prove that decreasing the regularization can indeed accelerate convergence. To this end, we introduce DRAG: Decreasing (entropic) Regularization Averaged Gradient, a stochastic gradient descent algorithm where the regularization decreases with the number of optimization steps. We provide a theoretical analysis showing that DRAG benefits from decreasing regularization compared to a fixed scheme, achieving an unbiased $\mathcal{O}(1/t)$ sample and iteration complexity for both the OT cost and the potential estimation, and a $\mathcal{O}(1/\sqrt{t})$ rate for the OT map. Our theoretical findings are supported by numerical experiments that validate the effectiveness of DRAG and highlight its practical advantages.

    • 30 October 2025
    • Published by HAL in HAL
    Open Access

    Decreasing Entropic Regularization Averaged Gradient for Semi-Discrete Optimal Transport

    by Ferdinand Genans, Antoine Godichon-Baggioni, François-Xavier Vialard, Olivier Wintenberger

    Adding entropic regularization to Optimal Transport (OT) problems has become a standard approach for designing efficient and scalable solvers. However, regularization introduces a bias from the true solution. To mitigate this bias while still benefiting from the acceleration provided by regularization, a natural solver would adaptively decrease the regularization as it approaches the solution. Although some algorithms heuristically implement this idea, their theoretical guarantees and the extent of their acceleration compared to using a fixed regularization remain largely open. In the setting of semi-discrete OT, where the source measure is continuous and the target is discrete, we prove that decreasing the regularization can indeed accelerate convergence. To this end, we introduce DRAG: Decreasing (entropic) Regularization Averaged Gradient, a stochastic gradient descent algorithm where the regularization decreases with the number of optimization steps. We provide a theoretical analysis showing that DRAG benefits from decreasing regularization compared to a fixed scheme, achieving an unbiased $\mathcal{O}(1/t)$ sample and iteration complexity for both the OT cost and the potential estimation, and a $\mathcal{O}(1/\sqrt{t})$ rate for the OT map. Our theoretical findings are supported by numerical experiments that validate the effectiveness of DRAG and highlight its practical advantages.

  • Open Access

    Stochastic Optimization in Semi-Discrete Optimal Transport: Convergence Analysis and Minimax Rate

    by Ferdinand Genans, Antoine Godichon-Baggioni, François-Xavier Vialard, Olivier Wintenberger

    We investigate the semi-discrete Optimal Transport (OT) problem, where a continuous source measure $μ$ is transported to a discrete target measure $ν$, with particular attention to the OT map approximation. In this setting, Stochastic Gradient Descent (SGD) based solvers have demonstrated strong empirical performance in recent machine learning applications, yet their theoretical guarantee to approximate the OT map is an open question. In this work, we answer it positively by providing both computational and statistical convergence guarantees of SGD. Specifically, we show that SGD methods can estimate the OT map with a minimax convergence rate of $\mathcal{O}(1/\sqrt{n})$, where $n$ is the number of samples drawn from $μ$. To establish this result, we study the averaged projected SGD algorithm, and identify a suitable projection set that contains a minimizer of the objective, even when the source measure is not compactly supported. Our analysis holds under mild assumptions on the source measure and applies to MTW cost functions,whic include $\|\cdot\|^p$ for $p \in (1, \infty)$. We finally provide numerical evidence for our theoretical results.

    • 1 September 2025
    • Published by HAL in HAL
    Open Access

    Robust Estimation for Linear State-Space Models with Stochastic Covariates

    by Jean-Luc Mahoromeza, Adeline Fermanian, Olivier Wintenberger, Joseph De Vilmarest

    The Kalman-Bucy filter (KF) is used to estimate and predict state-space models. It frequently encounters uncertain covariates, such as those derived from noisy measurements of physical signals (e.g., sensor readings, weather data, etc.). Our aim is to account for their uncertainties and develop robust KF approaches when incorporating the uncertainties of the covariates into the model—that is, by treating them as stochastic variables with known distributions. To enhance the robustness of the KF viewed as a Bayesian method that estimates the posterior distribution of the system state conditioned on past observations, we propose two methods. The linear Bayes estimator, which yields an explicit, unbiased forecast with minimal variance. An optimal risk estimator, which is non-linear and remains robust even when the covariates are highly noisy. This second method is approximated using a sequential Monte Carlo technique.

  • Open Access

    On the asymptotics of extremal $\ell ^p-$blocks cluster inference

    by Gloria Buriticá, Olivier Wintenberger

    Extremes occur in stationary regularly varying time series as short periods with several large observations, known as extremal blocks. We study cluster statistics summarizing the behavior of functions acting on these extremal blocks. Examples of cluster statistics are the extremal index, cluster size probabilities, and other cluster indices. The purpose of our work is twofold. First, we state the asymptotic normality of block estimators for cluster inference based on consecutive observations with large $$\ell ^p-$$ ℓ p - norms, for $$p > 0$$ p > 0 . The case $$p=\alpha $$ p = α , where $$\alpha > 0$$ α > 0 is the tail index of the time series, has specific nice properties thus we analyze the asymptotics of block estimators when approximating $${\alpha }$$ α using the Hill estimator. Second, we verify the conditions we require on classical models such as linear models and solutions of stochastic recurrence equations. Regarding linear models, we prove that the asymptotic variance of classical index cluster-based estimators is null as first conjectured in Hsing (Probab. Theory Related Fields 95 , 331–356 1993). We illustrate our findings on simulations.