English
Related papers

Related papers: Beyond Expectations: Learning with Stochastic Domi…

200 papers

Many of the successes of machine learning are based on minimizing an averaged loss function. However, it is well-known that this paradigm suffers from robustness issues that hinder its applicability in safety-critical domains. These issues…

Machine Learning · Computer Science 2022-06-09 Alexander Robey , Luiz F. O. Chamon , George J. Pappas , Hamed Hassani

In this study, we develop a stochastic optimal control approach with reinforcement learning structure to learn the unknown parameters appeared in the drift and diffusion terms of the stochastic differential equation. By choosing an…

Optimization and Control · Mathematics 2023-08-22 Shuzhen Yang

Safe Reinforcement Learning from Human Feedback (RLHF) typically enforces safety through expected cost constraints, but the expectation captures only a single statistic of the cost distribution and fails to account for distributional…

Machine Learning · Computer Science 2026-03-12 Yaswanth Chittepu , Ativ Joshi , Rajarshi Bhattacharjee , Scott Niekum

Stochastic optimization has found wide applications in minimizing objective functions in machine learning, which motivates a lot of theoretical studies to understand its practical success. Most of existing studies focus on the convergence…

Artificial Intelligence · Computer Science 2023-07-19 Yunwen Lei

It has been found that stochastic algorithms often find good solutions much more rapidly than inherently-batch approaches. Indeed, a very useful rule of thumb is that often, when solving a machine learning problem, an iterative technique…

Machine Learning · Computer Science 2013-08-19 Andrew Cotter

Comparisons of different treatments or production processes are the goals of a significant fraction of applied research. Unsurprisingly, two-sample problems play a main role in Statistics through natural questions such as `Is the the new…

Methodology · Statistics 2017-09-05 P. C. Álvarez-Esteban , E. del Barrio , J. A. Cuesta-Albertos , C. Matrán

To model combinatorial decision problems involving uncertainty and probability, we introduce stochastic constraint programming. Stochastic constraint programs contain both decision variables (which we can set) and stochastic variables…

Artificial Intelligence · Computer Science 2009-03-09 Toby Walsh

Approaches to keeping a dynamical system within state constraints typically rely on a model-based safety condition to limit the control signals. In the face of significant modeling uncertainty, the system can suffer from important…

Systems and Control · Electrical Eng. & Systems 2022-02-08 Marc-Antoine Beaudoin , Benoit Boulet

Stochastic gradient optimization is the dominant learning paradigm for a variety of scenarios, from classical supervised learning to modern self-supervised learning. We consider stochastic gradient algorithms for learning problems whose…

Machine Learning · Statistics 2025-08-29 Facheng Yu , Ronak Mehta , Alex Luedtke , Zaid Harchaoui

Existing approaches of prescriptive analytics -- where inputs of an optimization model can be predicted by leveraging covariates in a machine learning model -- often attempt to optimize the mean value of an uncertain objective. However,…

Machine Learning · Computer Science 2025-03-05 Dimitris Bertsimas , Benjamin Boucher

Optimization problems with stochastic dominance constraints provide a possibility to shape risk by selecting a benchmark random outcome with a desired distribution. The comparison of the relevant random outcomes to the respective benchmarks…

Optimization and Control · Mathematics 2025-09-09 Darinka Dentcheva , Yunxuan Yi

A common goal in statistics and machine learning is to learn models that can perform well against distributional shifts, such as latent heterogeneous subpopulations, unknown covariate shifts, or unmodeled temporal effects. We develop and…

Machine Learning · Statistics 2020-07-21 John Duchi , Hongseok Namkoong

Decision Focused Learning has emerged as a critical paradigm for integrating machine learning with downstream optimisation. Despite its promise, existing methodologies predominantly rely on probabilistic models and focus narrowly on task…

Machine Learning · Computer Science 2025-03-21 Keivan Shariatmadar , Neil Yorke-Smith , Ahmad Osman , Fabio Cuzzolin , Hans Hallez , David Moens

We study the problem of learning-to-learn: inferring a learning algorithm that works well on tasks sampled from an unknown distribution. As class of algorithms we consider Stochastic Gradient Descent on the true risk regularized by the…

Machine Learning · Computer Science 2019-03-26 Giulia Denevi , Carlo Ciliberto , Riccardo Grazzi , Massimiliano Pontil

In performative stochastic optimization, decisions can influence the distribution of random parameters, rendering the data-generating process itself decision-dependent. In practice, decision-makers rarely have access to the true…

Optimization and Control · Mathematics 2025-10-27 Zhuangzhuang Jia , Yijie Wang , Roy Dong , Grani A. Hanasusanto

Non-deterministic measurements are common in real-world scenarios: the performance of a stochastic optimization algorithm or the total reward of a reinforcement learning agent in a chaotic environment are just two examples in which…

Machine Learning · Statistics 2022-08-31 Etor Arza , Josu Ceberio , Ekhiñe Irurozki , Aritz Pérez

We propose a statistically optimal approach to construct data-driven decisions for stochastic optimization problems. Fundamentally, a data-driven decision is simply a function that maps the available training data to a feasible action. It…

Optimization and Control · Mathematics 2023-12-18 Tobias Sutter , Bart P. G. Van Parys , Daniel Kuhn

In many real-world scenarios, the utility of a user is derived from the single execution of a policy. In this case, to apply multi-objective reinforcement learning, the expected utility of the returns must be optimised. Various scenarios…

Machine Learning · Computer Science 2022-07-06 Conor F. Hayes , Timothy Verstraeten , Diederik M. Roijers , Enda Howley , Patrick Mannion

The concept of "stochastic precedence" between two real-valued random variables has often emerged in different applied frameworks. In this paper we consider a slightly more general, and completely natural, concept of stochastic precedence…

Probability · Mathematics 2015-06-17 Emilio De Santis , Fabio Fantozzi , Fabio Spizzichino

In reinforcement learning episodes, the rewards and punishments are often non-deterministic, and there are invariably stochastic elements governing the underlying situation. Such stochastic elements are often numerous and cannot be known in…

Machine Learning · Computer Science 2019-02-13 Nikki Lijing Kuang , Clement H. C. Leung , Vienne W. K. Sung