stat.ML · 2026-05-28 · No. 11

Machine Learning, 2026-05-28.

8 new papers in stat.ML. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

8 entries

01

Beyond Lipschitz: Data-Driven Robustness via Discrete Modulus of Continuity

Jürgen Dölz, Michael Multerer, Michele Palma

stat.ML · cs.LG

Robustness of neural networks is commonly quantified via local or global Lipschitz constants. However, Lipschitz continuity can be overly coarse or overly restrictive as global robustness measure, failing to capture nuanced, data-dependent behavior. We propose a data-driven, architecture-agnostic framework based on the discrete modulus of continuity (DMOC), a non linear generalization of Lipschitz continuity that provides a finer notion of...

arxiv.org/abs/2605.28729 · PDF
02

Conservative neural posterior estimation via distributionally robust training

William Laplante, Yuga Hikida, Charita Dellaporta, François-Xavier Briol, Ayush Bharti

stat.ML · cs.LG

Simulation-based inference with neural posterior estimation (NPE) often yields overconfident and unreliable posteriors under limited simulation budgets. To address this, we propose DRO-NPE, a distributionally robust approach that replaces the standard NPE objective with a worst-case loss over a Wasserstein ambiguity set. We introduce KL-based metrics for miscoverage and miscalibration, and use these to show that the DRO-NPE objective controls...

arxiv.org/abs/2605.28516 · PDF
03

Bridging Maximum Likelihood and Optimal Transport for Efficient Inference and Model Selection in Stochastic Block Models

Simon Queric, Cédric Vincent-Cuaz, Charles Bouveyron, Marco Corneli

stat.ML · cs.LG · math.ST

We study inference in stochastic block models (SBMs) through the lens of optimal transport (OT). We first establish that maximum likelihood variational inference (MLVI) can be interpreted as a semi-relaxed Gromov-Wasserstein (srGW) projection with entropic regularization. While this formulation yields accurate clustering, the entropic regularization prevents transport plans to be sparse, hindering intrinsic model selection. Consequently, we...

arxiv.org/abs/2605.28488 · PDF
04

Variance-Adaptive Optimal Algorithm for Reinforcement Learning with Multinomial Logit Function Approximation

Wonyoung Kim, Min-Hwan Oh, Garud Iyengar, Assaf Zeevi

stat.ML · cs.LG

Reinforcement learning with multinomial logistic (MNL) function approximation has become an important framework due to its flexibility and broad applicability. While existing studies have established regret guarantees under worst-case analysis, they do not capture how performance depends on the variability of the interaction between the learner and the environment. In this paper, we develop a new theoretical analysis for MNL-based Markov...

arxiv.org/abs/2605.28364 · PDF
05

Decision-focused learning for optimal PV-Battery scheduling

Joris Depoortere, Hussain Kazmi, Johan Driesen

stat.ML · cs.LG

The use of residential photovoltaics has increased dramatically in recent years. With battery systems becoming more affordable, the optimal operation of a photovoltaic-battery system can bring significant savings to households. Optimal control requires correct forecasts of underlying parameters, such as photovoltaic power generation, to schedule the battery. While forecasting models have become increasingly accurate due to algorithmic...

arxiv.org/abs/2605.28340 · PDF
06

Insurance Pricing Optimization via Off-Policy Evaluation

Sascha Günther, Dimitri Semenovich, Mario V. Wüthrich

stat.ML · cs.LG · q-fin.RM · stat.AP

Traditional insurance pricing relies on risk-based principles that ensure actuarial fairness and solvency but do not explicitly account for policyholders' price sensitivity. We formulate insurance pricing as a decision-making problem and study it using tools from off-policy evaluation and stochastic control. We propose a kernelized inverse propensity score estimator that exploits local structure in the action space and yields variance...

arxiv.org/abs/2605.28327 · PDF
07

Counterfactually Fair Regression via Optimal Transport

M. Generali Lince, S. Gaucher, J-J. Vie, P. Loiseau

stat.ML · cs.CY · cs.LG

We consider the problem of learning a counterfactually fair regressor. We adopt a causal uncertainty view in which counterfactual fairness is defined with resampled noise. We focus on obtaining theoretical fairness guarantees for a new post-processing estimator. We begin by showing that counterfactual fairness is equivalent to satisfying demographic parity conditional on the latent variable. This allows us to provide a closed-form expression...

arxiv.org/abs/2605.28251 · PDF
08

Geometry of Relaxed Fair Regression: A Unified Framework for Aware and Unaware Settings

M. Generali Lince, V. Divol, R. Flamary, S. Gaucher, P. Loiseau

stat.ML · cs.CY · cs.LG

Fairness-accuracy trade-offs are a central concern in the deployment of fairness-aware machine learning methods. When sensitive attributes are unavailable at inference time-the so called unawareness setting, principled methods for obtaining accurate predictions under relaxed fairness constraints are largely missing. In this work, we address this gap by formulating regression under a demographic parity penalty as an optimal transport problem....

arxiv.org/abs/2605.28233 · PDF

This edition is part of The Daily Abstract — stat.ML archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.