Predict-Then-Optimize

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 20

All topics

FedRSPO+: A Heterogeneity-aware Algorithm for Decision-focused Federated Learning
Oct 6, 2026Konstantinos Ziliaskopoulos, Alexander Vinel, Jiaqi WangDecision-Focused Learning Federated Learning
Auburn University
DePICT: Decision-Preserving Interface for Constrained Downstream Tasks
Oct 2, 2026Utkarsh Grover, Ravi Ranjan, Agoritsa Polyzou +4Predict-Then-Optimize Constrained Optimization
University of South Florida · Florida International University · DEVCOM Army Research Lab
Geometric Identification in Predict-Then-Optimize Learning
Sep 27, 2026Jiaxiao Xu, Changhong Mou, Keji Liu +2Predict-Then-Optimize Decision-Focused Learning
Shanghai University of Finance and Economics · Utah State University
Eigenvalue-Decomposition Cost Denoising as an Alternative to Predict-then-Optimize for Shortest-Path Problems
Sep 14, 2026Henry Aldridge-Krawciw, Irene AldridgePredict-Then-Optimize Combinatorial Optimization
Optimizing for the decision not the prediction: an exploration of Smooth Net Benefit as a training objective
Sep 14, 2026Koen M. F. Gorgels, Lasai Barreñada, Maarten van Smeden +3Predict-Then-Optimize Decision-Focused Learning
Department of Data Science and Biostatistics, Julius Center for Health Sciences and Primary Care, University Medical Center Utrecht, Utrecht, the Netherlands · Coo peratie VGZ, Arnhem, the Netherlands · Department of Development and Regeneration, KU Leuven, Leuven, Belgium
Chance-constrained selection of sequential intervention strategies from counterfactual estimates
Aug 13, 2026Minkyoung Kim, Beakcheol JangStochastic Optimization Chance-Constrained Optimization
Graduate School of Information, Yonsei University, 50 Yonsei-ro, Seodaemun-gu, Seoul, 03722, Republic of Korea
Local Violation Certification for Linear Predict-Then-Optimize Pipelines
Aug 5, 2026Ş. İlker Birbil, Wenhao ChiAlgorithmic Auditing Predict-Then-Optimize
Faculty of Economics and Business, University of Amsterdam, The Netherlands · Yau Mathematical Sciences Center, Tsinghua University
Smart predict-then-robustly-optimize
Jul 23, 2026Aakil Caunhye, Xuefei Lu, Belen Martin-BarraganDistribution Shift Robustness Predict-Then-Optimize
Decision-Value Attribution in Predict-then-Optimize Systems
Jun 29, 2026Konstantinos Ziliaskopoulos, Alexander Vinel, Alice E. SmithFeature Attribution Predict-Then-Optimize
Auburn University, Industrial & Systems Engineering, 36849, Auburn, AL, USA · University of Alabama, Mechanical Engineering & Computer Science, 35487, Tuscaloosa, AL, USA
Generating Input Distributions for Explaining Portfolio Optimization Pipelines
Jun 24, 2026Batuhan Ataş, Nurşen Aydın, E. Mehmet Kıral +1Counterfactual Explanations Predict-Then-Optimize
Faculty of Economics and Business, University of Amsterdam, The Netherlands · Warwick Business School, University of Warwick, United Kingdom · RIKEN AIP, Japan
Decision-Focused Learning: When and Why Traditional Prediction Models Fail
Jun 19, 2026Mo LiuPredict-Then-Optimize Decision-Focused Learning
Department of Statistics and Operations Research, University of North Carolina at Chapel Hill
A Solver-Free Training Method for Predict-then-Optimize
Jun 17, 2026Beichen Wan, Mo LiuPredict-Then-Optimize Learning to Optimize
Department of Statistics and Operations Research, University of North Carolina at Chapel Hill, NC, USA.
Scaling Decision-Focused Learning to Large Problems with Lagrangian Decomposition
Jun 7, 2026Stéphane Eilles-Chan Way, Hugo Percot, Quentin Cappart +2Predict-Then-Optimize Learning to Optimize
Polytechnique Montréal, Montreal, Canada · Ecole Polytechnique, Palaiseau, France · UCLouvain, Louvain-la-Neuve, Belgium +2
Decision-Focused On-Policy Learning for Contextual Linear Optimization with Partial Feedback
May 31, 2026Wyame Benslimane, Tinghan Ye, Pascal Van Hentenryck +1Predict-Then-Optimize Decision-Focused Learning
Department of Industrial Engineering and Operations Research University of California, Berkeley · H. Milton Stewart School of Industrial and Systems Engineering Georgia Institute of Technology
Misspecified Estimate-then-Optimize Leads to Supra-Competitive Prices
May 15, 2026Jackie Baek, Vivek F. Farias, Farrell WuPredict-Then-Optimize Learning to Optimize
Stern School of Business, New York University · Massachusetts Institute of Technology
IGT-OMD: Implicit Gradient Transport for Decision-Focused Learning under Delayed Feedback
May 12, 2026Benjamin Amoh, Geoffrey G. Parker, Wesley MarreroPredict-Then-Optimize Decision-Focused Learning
Thayer School of Engineering, Dartmouth College
Plan Before You Trade: Inference-Time Optimization for RL Trading Agents
May 12, 2026Eun Go, Rohan Deb, Arindam BanerjeeReinforcement Learning Inference-Time Optimization
Siebel School of Computing and Data Science University of Illinois Urbana-Champaign
Decision-Focused Federated Learning Under Heterogeneous Objectives and Constraints
Apr 21, 2026Konstantinos Ziliaskopoulos, Alexander VinelPredict-Then-Optimize Learning to Optimize
Auburn University
Deep Learning for Sequential Decision Making under Uncertainty: Foundations, Frameworks, and Frontiers
Apr 13, 2026I. Esra BuyuktahtakinReinforcement Learning Predict-Then-Optimize
Grado Department of Industrial and Systems Engineering, Virginia Tech Blacksburg, VA 24061, USA
Simulating Classification Models for Ex-Ante Evaluation of Predict-Then-Optimize Methods
Sep 2, 2025Pieter SmetPredict-Then-Optimize
KU Leuven, Department of Computer Science, NUMA · Gebroeders De Smetstraat 1, 9000 Gent, Belgium

Oct 6, 2026, cs.LGJ/K move · Enter open · S save

FedRSPO+: A Heterogeneity-aware Algorithm for Decision-focused Federated Learning

Konstantinos Ziliaskopoulos, Alexander Vinel, Jiaqi Wang

Auburn University

Decision-Focused Learning Federated Learning Predict-Then-Optimize Heterogeneous Federated Learning

Open paper AskPDF arXiv

Decision-focused learning (DFL) trains predictive models for downstream optimization, but existing methods largely assume centralized data. In cross-silo settings, federated learning offers a natural alternative, yet standard federated methods optimize prediction over decision quality and do not address heterogeneity in downstream objectives or feasible sets. This heterogeneity is especially challenging for DFL because small perturbations in polyhedral problems can cause discontinuous changes in optimal decisions, destabilizing client updates and aggregation. We propose FedRSPO+, a heterogeneity-aware framework for decision-focused federated learning, built on RSPO+, a regularized predict-then-optimize surrogate that smooths the decision map through projection. We show that RSPO+ upper bounds decision error and regret for the regularized decision and, under exact regularization and consistent LP solution selection, for the original LP decision. We further derive cross-client heterogeneity bounds that depend on both objective and feasible-set heterogeneity, vanish at homogeneity, and require no strong convexity. FedRSPO+ uses an annealed, modular training procedure compatible with standard federated personalization and aggregation methods. Experiments on synthetic knapsack, shortest-path, and real-world energy pricing tasks compare against prediction-only federated learning and DFL baselines under varying heterogeneity and communication budgets. Results suggest that smoothing is a useful ingredient for stable collaborative decision learning and provide a heterogeneity-aware foundation for federated DFL.

Momentum

Related topics

Latest papers 20