learning-to-optimize – Optimization Online

Deep Learning for Sequential Decision Making under Uncertainty: Foundations, Frameworks, and Frontiers

Published: 2026/04/12

Data Science Algorithms, Optimization in Data Science, Stochastic Programming decision making under uncertainty, Decision-focused learning, deep learning, learning-to-optimize, Machine learning and optimization, markov decision processes, multi-stage stochastic programming, operations research, optimization under uncertainty, reinforcement learning, sequential decision making, stochastic optimization

Artificial intelligence (AI) is moving increasingly beyond prediction to support decisions in complex, uncertain, and dynamic environments. This shift creates a natural intersection with operations research and management sciences (OR/MS), which have long offered conceptual and methodological foundations for sequential decision-making under uncertainty. At the same time, recent advances in deep learning, including feedforward neural … Read more

A Generalization Result for Convergence in Learning-to-Optimize

Published: 2024/10/10

Michael Sucker

Peter Ochs

Convex and Nonsmooth Optimization, Nonsmooth Optimization, Optimization in Data Science learning-to-optimize, pac-bayes, stationary points

Convergence in learning-to-optimize is hardly studied, because conventional convergence guarantees in optimization are based on geometric arguments, which cannot be applied easily to learned algorithms. Thus, we develop a probabilistic framework that resembles deterministic optimization and allows for transferring geometric arguments into learning-to-optimize. Our main theorem is a generalization result for parametric classes of potentially … Read more

A Markovian Model for Learning-to-Optimize

Published: 2024/08/21

Michael Sucker

Peter Ochs

Optimization in Data Science, Stochastic Approaches, Stochastic Programming convergence rate, learning-to-optimize, pac-bayes, stochastic processes, stopping time

We present a probabilistic model for stochastic iterative algorithms with the use case of optimization algorithms in mind. Based on this model, we present PAC-Bayesian generalization bounds for functions that are defined on the trajectory of the learned algorithm, for example, the expected (non-asymptotic) convergence rate and the expected time to reach the stopping criterion. … Read more

Learning-to-Optimize with PAC-Bayesian Guarantees: Theoretical Considerations and Practical Implementation

Published: 2024/04/04, Updated: 2025/02/25

Michael Sucker

Jalal Fadili

Peter Ochs

Optimization in Data Science, Other Topics learning-to-optimize, pac-bayes

We use the PAC-Bayesian theory for the setting of learning-to-optimize. To the best of our knowledge, we present the first framework to learn optimization algorithms with provable generalization guarantees (PAC-Bayesian bounds) and explicit trade-off between convergence guarantees and convergence speed, which contrasts with the typical worst-case analysis. Our learned optimization algorithms provably outperform related ones … Read more