Decision-Focused On-Policy Learning for Contextual Linear Optimization with Partial Feedback

• URL: http://arxiv.org/abs/2606.01081v1
• Date: Sun, 31 May 2026 07:58:28 GMT
• Title: Decision-Focused On-Policy Learning for Contextual Linear Optimization with Partial Feedback
• Abstract summary: Decision-focused learning (DFL) trains predictive models by optimizing downstream decision quality rather than standalone prediction accuracy.<n>For contextual linear optimization, most existing DFL methods assume offline full observations of objective vector.<n>We introduce a two-component hybrid estimator to update a conditional distributional model.
• Score: 14.912614425471915
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Decision-focused learning (DFL) trains predictive models by optimizing downstream decision quality rather than standalone prediction accuracy. For contextual linear optimization, most existing DFL methods assume offline data and full observations of the objective cost vector. We develop an on-policy learning method for sequential contextual linear optimization under partial feedback, generalizing the standard bandit feedback setting. Our method learns a stochastic predict-then-optimize policy that samples a cost-vector prediction from a conditional distribution and solves the resulting downstream linear optimization problem. To update this distributional model, we introduce a two-component hybrid gradient estimator. The first component is a score function estimator, which provides an unbiased but potentially high-variance policy gradient estimate. The second is a decision-focused plug-in component that uses an auxiliary nuisance estimate of the latent cost vector to exploit the downstream optimization structure, becoming more informative as the estimate improves. We prove an $\mathcal{O}(T^{-1/2})$ bound on the average squared policy-gradient norm, matching the standard non-convex SGD rate. Experiments on top-$k$ selection, shortest path, combinatorial pricing, and a real-data energy-scheduling benchmark show that the hybrid gradient approach achieves lower cumulative regret than contextual-bandit-style baselines across all benchmarks, using both Gaussian and richer conditional generative models. Code is available at https://github.com/Joeyetinghan/on-policy-bandit-dfl.

Related papers

• Bandit Convex Optimization with Gradient Prediction Adaptivity [56.816177049016794]
  We investigate whether optimistic gradient predictions can improve worst-case regret guarantees in a prediction-adaptive manner.<n>The key idea is a novel variance-reduced gradient estimator whose variance scales with the prediction error rather than the gradient norm.<n>We establish an information-theoretic lower bound that scales as $(sqrtmathbbE[S_T])$, providing a fundamental characterization of the best achievable prediction-adaptive regret.
  arXiv  Detail & Related papers  (2026-05-21T08:57:38Z)
• Contextual Preference Distribution Learning [5.872632454395936]
  We propose a sequential learning-and-optimization pipeline to learn preference distributions and leverage them to solve downstream problems.<n>We focus on human choice settings that can be formulated as (integer) linear programs.
  arXiv  Detail & Related papers  (2026-03-17T21:11:21Z)
• Zero-Order Optimization for LLM Fine-Tuning via Learnable Direction Sampling [40.94400211806987]
  We propose a policy-driven ZO framework that treats the sampling distribution over perturbation directions as a learnable policy.<n>We show that learned sampling improves quality gradient information and relax the explicit dependence on $d$ in convergence bounds.<n>Our results suggest that adaptive direction sampling is a promising route to make ZO fine-tuning viable at scale.
  arXiv  Detail & Related papers  (2026-02-14T08:01:41Z)
• On the Optimal Construction of Unbiased Gradient Estimators for Zeroth-Order Optimization [57.179679246370114]
  A potential limitation of existing methods is the bias inherent in most perturbation estimators unless a stepsize is proposed.<n>We propose a novel family of unbiased gradient scaling estimators that eliminate bias while maintaining favorable construction.
  arXiv  Detail & Related papers  (2025-10-22T18:25:43Z)
• From Noisy Traces to Stable Gradients: Bias-Variance Optimized Preference Optimization for Aligning Large Reasoning Models [90.45197506653341]
  Large reasoning models generate intermediate reasoning traces before producing final answers.<n> aligning LRMs with human preferences, a crucial prerequisite for model deployment, remains underexplored.<n>A common workaround optimized a single sampled trajectory, which introduces substantial gradient variance from trace sampling.
  arXiv  Detail & Related papers  (2025-10-06T17:58:01Z)
• Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing [58.52119063742121]
  Retraining a model using its own predictions together with the original, potentially noisy labels is a well-known strategy for improving the model performance.<n>This paper addresses the question of how to optimally combine the model's predictions and the provided labels.<n>Our main contribution is the derivation of the Bayes optimal aggregator function to combine the current model's predictions and the given labels.
  arXiv  Detail & Related papers  (2025-05-21T07:16:44Z)
• Calibrated Multi-Preference Optimization for Aligning Diffusion Models [90.15024547673785]
  Calibrated Preference Optimization (CaPO) is a novel method to align text-to-image (T2I) diffusion models.<n>CaPO incorporates the general preference from multiple reward models without human annotated data.<n> Experimental results show that CaPO consistently outperforms prior methods.
  arXiv  Detail & Related papers  (2025-02-04T18:59:23Z)
• Contextual Linear Optimization with Partial Feedback [35.38485630117593]
  We propose a class of offline learning algorithms for Contextual linear optimization (CLO) with different types of feedback.<n>We provide a novel fast-rate regret bound for IERM that allows for misspecified model classes and flexible choices of estimation methods.
  arXiv  Detail & Related papers  (2024-05-26T13:27:27Z)
• DF2: Distribution-Free Decision-Focused Learning [30.288876294435294]
  Decision-focused learning (DFL) has emerged as a powerful approach for predict-then-optimize problems.<n>DFL faces three bottlenecks: model error, sample average approximation error, and approximation error.<n>We present DF2, the first decision-free learning method designed to mitigate these three bottlenecks.
  arXiv  Detail & Related papers  (2023-08-11T00:44:46Z)
• Offline Primal-Dual Reinforcement Learning for Linear MDPs [16.782625445546273]
  Offline Reinforcement Learning (RL) aims to learn a near-optimal policy from a fixed dataset of transitions collected by another policy. This paper proposes a primal-dual optimization method based on the linear programming formulation of RL.
  arXiv  Detail & Related papers  (2023-05-22T11:45:23Z)
• Online Contextual Decision-Making with a Smart Predict-then-Optimize Method [4.061135251278187]
  We study an online contextual decision-making problem with resource constraints. We propose an algorithm that mixes a prediction step based on the "Smart Predict-then- (SPO)" method with a dual update step based on mirror descent. We prove regret bounds and demonstrate that the overall convergence rate of our method depends on the $mathcalO(T-1/2)$ convergence of online mirror descent.
  arXiv  Detail & Related papers  (2022-06-15T06:16:13Z)
• Private Stochastic Non-Convex Optimization: Adaptive Algorithms and Tighter Generalization Bounds [72.63031036770425]
  We propose differentially private (DP) algorithms for bound non-dimensional optimization. We demonstrate two popular deep learning methods on the empirical advantages over standard gradient methods.
  arXiv  Detail & Related papers  (2020-06-24T06:01:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.