End-to-End Learning for Stochastic Optimization: A Bayesian Perspective

Yves Rychener, D. Kuhn, Tobias Sutter
2/12/2026

No official code found. Best implementation: RAO-EPFL/end2end-SO (5 stars, MIT, last commit 2024-02-15).

Abstract

We develop a principled approach to end-to-end learning in stochastic optimization. First, we show that the standard end-to-end learning algorithm admits a Bayesian interpretation and trains a posterior Bayes action map. Building on the insights of this analysis, we then propose new end-to-end learning algorithms for training decision maps that output solutions of empirical risk minimization and distributionally robust optimization problems, two dominant modeling paradigms in optimization under uncertainty. Numerical results for a synthetic newsvendor problem illustrate the key differences between alternative training schemes. We also investigate an economic dispatch problem based on real data to showcase the impact of the neural network architecture of the decision maps on their test performance.

View on arXivView PDF

Code Implementations(1)

RAO-EPFL/end2end-SOCommunity71%
MIT

Code for Paper 'End-to-End Learning for Stochastic Optimization: A Bayesian Perspective'

51PythonMay 1, 20232 years agoMIT

Similar Papers

Efficient End-to-End Learning for Decision-Making: A Meta-Optimization Approach

84% match2025

End-to-End Learning for Fair Multiobjective Optimization Under Uncertainty

83% match2024

Aligning Learning and Endogenous Decision-Making

83% match2025

A Generalization Result for Convergence in Learning-to-Optimize

82% match2026

Beyond Single-Model Views for Deep Learning: Optimization versus Generalizability of Stochastic Optimization Algorithms

81% match2024

A Reinforcement Learning Method for Environments with Stochastic Variables: Post-Decision Proximal Policy Optimization with Dual Critic Networks

81% match1 repo12025

Cite this paper

@article{rychener2026endtoend,
  title  = {End-to-End Learning for Stochastic Optimization: A Bayesian Perspective},
  author = {Yves Rychener and D. Kuhn and Tobias Sutter},
  year   = {2026},
  eprint = {2306.04174},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/pdf/2306.04174},
  journal = {ICML 2023 2023}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2306.04174.svg)](https://codeofpaper.com/paper/2306.04174)

Discussion