Search Results - subject:"Machine Learning and Data Science"

Global optimality guarantees for policy gradient methods

Bhandari, Jalaj; Russo, Daniel - In: Operations research 72 (2024) 5, pp. 1906-1927

Persistent link: https://www.econbiz.de/10015361758

Model-based reinforcement learning for offline zero-sum Markov games

Yan, Yuling; Li, Gen; Chen, Yuxin; Fan, Jianqing - In: Operations research 72 (2024) 6, pp. 2430-2445

Persistent link: https://www.econbiz.de/10015371449

Breaking the sample size barrier in model-based reinforcement learning with a generative model

Li, Gen; Wei, Yuting; Chi, Yuejie; Chen, Yuxin - In: Operations research 72 (2024) 1, pp. 203-221

Persistent link: https://www.econbiz.de/10014505071

Is Q-learning minimax optimal? : a tight sample complexity analysis

Li, Gen; Cai, Changxiao; Chen, Yuxin; Wei, Yuting; Chi, … - In: Operations research 72 (2024) 1, pp. 222-236

Persistent link: https://www.econbiz.de/10014505079

Nonconvex low-rank tensor completion from noisy data

Cai, Changxiao; Li, Gen; Poor, H. Vincent; Chen, Yuxin - In: Operations research 70 (2022) 2, pp. 1219-1237

Persistent link: https://www.econbiz.de/10013365875

Fast global convergence of natural policy gradient methods with entropy regularization

Cen, Shicong; Cheng, Chen; Chen, Yuxin; Wei, Yuting; … - In: Operations research 70 (2022) 4, pp. 2563-2578

Persistent link: https://www.econbiz.de/10013366515

A combined neural network approach for the prediction of admission rates related to respiratory diseases

Jose, Alex; Macdonald, Angus; Tzougas, George; … - In: Risks : open access journal 10 (2022) 11, pp. 1-35

In this paper, we investigated rates of admission to hospitals (or other health facilities) due to respiratory diseases in a United States working population and their dependence on a number of demographic and health insurance-related factors. We employed neural network (NN) modelling...

Persistent link: https://www.econbiz.de/10014228893

A pareto dominance principle for data-driven optimization

Sutter, Tobias; Parys, Bart P. G. van; Kuhn, Daniel - In: Operations research 72 (2024) 5, pp. 1976-1999

Persistent link: https://www.econbiz.de/10015361762

An algorithmic solution to the blotto game using multimarginal couplings

Perchet, Vianney; Rigollet, Philippe; Le Gouic, Thibaut - In: Operations research 72 (2024) 5, pp. 2061-2075

Persistent link: https://www.econbiz.de/10015361766

Recursive importance sketching for rank constrained least squares : algorithms and high-order convergence

Luo, Yuetian; Huang, Wen; Li, Xudong; Zhang, Anru - In: Operations research 72 (2024) 1, pp. 237-256

Persistent link: https://www.econbiz.de/10014505097