arXiv AI
Jun 2
Regularized Offline Policy Optimization with Posterior Hybrid Bayesian Belief
arXiv:2606. 00680v1 Announce Type: new Abstract: Offline reinforcement learning (RL) aims to optimize policies from pre-collected datasets.
How much Data do We Need? Sequential Data Collection for Stochastic Programming
arXiv:2607. 10207v1 Announce Type: cross Abstract: Data-driven optimization often requires collecting data to estimate uncertain model parameters before solving the underlying decision problem.
Related stories
arXiv Machine Learning
Jul 21
Regret Optimality of Sample Average Approximation for Data-Driven Newsvendor Problems: A General Optimization Perspective
arXiv:2407. 04900v2 Announce Type: replace Abstract: Numerous existing studies have examined the performance of Sample Average Approximation (SAA) in the fundamental newsvendor problem.
arXiv Machine Learning
Jun 17
QueryMarket: Cost-Aware Online Active Learning in Data Markets
arXiv:2606. 17805v1 Announce Type: new Abstract: Data acquisition is a major bottleneck for learning in real-time streams: analysts must decide on the fly which labels to purchase while respecting a rolling budget.
arXiv Statistics ML
3d ago
Towards Optimal Inventory Control under Censored Demand: A Biased Sample-Average Approximation Approach
The paper presents a data‑driven framework for multi‑period lost‑sales inventory control when demand is censored, meaning stockouts only reveal that demand exceeded the stocking level. It introduces a new cost decomposition for base‑stock policies and a biased sample‑average approximation (SAA) method, leading to two algorithms: an upper‑biased SAA that achieves near‑optimal sample complexity under an offline coverage condition, and a lower‑biased SAA that actively generates coverage to achieve near‑optimal online regret. The biased SAA approach offers a general principle for applying pessimism and optimism in settings with censored feedback.
arXiv AI
Jul 7
Strategic Buying Agents
arXiv:2607. 04708v1 Announce Type: cross Abstract: Agentic AI is shifting online shopping from search toward delegated purchasing, where autonomous buying agents monitor markets and decide when to buy on a consumer's behalf.
arXiv Machine Learning
Jul 30
Collaborative Weighting with Pessimistic Critic for Mitigating Overestimation in Off-Policy Reinforcement Learning
arXiv:2607. 26509v1 Announce Type: new Abstract: Deep off-policy reinforcement learning algorithms for continuous control typically rely on neural value function approximation to guide policy improvement.
arXiv Machine Learning
Sep 22
Thompson Sampling for Infinite-Horizon Discounted Decision Processes
arXiv:2405.08253v4 Announce Type: replace-cross Abstract: This paper develops a framework for learning in discounted infinite-horizon Markov decision processes (MDPs) with Borel state and action spac...
arXiv Statistics ML
Sep 24
BOCO: Bayesian Online Contextual Optimization for Decision-Focused Online Learning
arXiv:2511.20413v2 Announce Type: replace-cross Abstract: \emph{Decision-focused learning} (DFL) trains predictive models to optimize downstream decisions rather than prediction accuracy alone. While...
arXiv Machine Learning
Aug 4
Learning-Based Stochastic Optimal Control with Infinite-Horizon Probabilistic Constraints
arXiv:2608. 01151v1 Announce Type: cross Abstract: In this paper, we consider stochastic optimal control problems with infinite-horizon joint chance constraints.
arXiv Machine Learning
Sep 7
Optimal Data Acquisition for Reinforcement Learning: A Large Deviations Perspective
The paper presents a large deviations framework for efficient data acquisition in infinite-horizon reinforcement learning, introducing the exponential decay rate of policy-selection error probability as a key efficiency metric. It derives a variational characterization leading to a nested optimization problem, then proposes a tractable convex relaxation and a lazy one-step projected subgradient method to construct an adaptive data acquisition policy. The resulting algorithm is shown to be near-robustly optimal under the proposed criterion, with extensions to linear function approximation and supporting numerical experiments.
arXiv AI
Jul 14
Learning to Fine-tune Foundation Models under Resource Limitations
arXiv:2607. 10694v1 Announce Type: cross Abstract: We study the problem of optimal continual fine-tuning for a pre-trained Foundation Model deployed at a resource-limited device.
arXiv Machine Learning
Jun 5
Cross-Epoch Adaptive Rollout Optimization for RL Post-Training
arXiv:2606. 05606v1 Announce Type: new Abstract: LLM post-training often relies on reinforcement learning methods that sample multiple rollouts per prompt, yet most existing approaches use a fixed rollout budget for every prompt, despite large differences in the training signal different prompts provide.