What' s the Harm? Sharp Bounds on the Fraction Negatively Affected by Treatment

von Kallus, Nathan
Veröffentlicht in NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 21 of 50 (2023)

Dynamic assortment personalization in high dimensions

von Kallus, Nathan
Veröffentlicht in Operations research (2020)

DOUBLY ROBUST OFF-POLICY VALUE AND GRADIENT FOR ESTIMATION FOR DETERMINISTIC POLICIES

von Kallus, Nathan
Veröffentlicht in NeurIPS (34. : 2020 : Online) 34th Conference on Neural Information Processing Systems (NeurIPS 2020) ; Volume 13 of 27 (2021)

CONFOUNDING-ROBUST POLICY EVALUATION IN INFINITE-HORIZON REINFORCEMENT LEARNING

von Kallus, Nathan
Veröffentlicht in NeurIPS (34. : 2020 : Online) 34th Conference on Neural Information Processing Systems (NeurIPS 2020) ; Volume 27 of 27 (2021)

EFFICIENT POLICY LEARNING FROM SURROGATE-LOSS CLASSIFICATION REDUCTIONS

von Bennett, Andrew
Veröffentlicht in International Conference on Machine Learning (37. : 2020 : Online) 37th International Conference on Machine Learning (ICML 2020) ; Part 1 of 15 (2021)

INTRINSICALLY EFFICIENT, STABLE, AND BOUNDED OFF-POLICY EVALUATION FORREINFORCEMENT LEARNING

von Kallus, Nathan
Veröffentlicht in NeurIPS (33. : 2019 : Vancouver, British Columbia) 32nd Conference on Neural Information Processing Systems (NeurIPS 2019) ; Volume 5 of 20 (2020)

POLICY EVALUATION WITH LATENT CONFOUNDERS VIA OPTIMAL BALANCE

von Bennett, Andrew
Veröffentlicht in NeurIPS (33. : 2019 : Vancouver, British Columbia) 32nd Conference on Neural Information Processing Systems (NeurIPS 2019) ; Volume 7 of 20 (2020)

Minimax-optimal policy learning under unobserved confounding

von Kallus, Nathan
Veröffentlicht in Management science (2021)

From predictive to prescriptive analytics

von Bertsimas, Dimitris
Veröffentlicht in Management science (2020)

ASSESSING DISPARATE IMPACT OF PERSONALIZED INTERVENTIONS: IDENTIFIABILITY AND BOUNDS

von Kallus, Nathan
Veröffentlicht in NeurIPS (33. : 2019 : Vancouver, British Columbia) 32nd Conference on Neural Information Processing Systems (NeurIPS 2019) ; Volume 5 of 20 (2020)

THE FAIRNESS OF RISK SCORES BEYOND CLASSIFICATION: BIPARTITE RANKING AND THE XAUC METRIC

von Kallus, Nathan
Veröffentlicht in NeurIPS (33. : 2019 : Vancouver, British Columbia) 32nd Conference on Neural Information Processing Systems (NeurIPS 2019) ; Volume 5 of 20 (2020)

The Implicit Delta Method

von Kallus, Nathan
Veröffentlicht in NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 48 of 50 (2023)

OPTIMAL OFF-POLICY EVALUATION FROM MULTIPLE LOGGING POLICIES

von KALLUS, NATHAN
Veröffentlicht in International Conference on Machine Learning (38. : 2021 : Online) International Conference on Machine Learning (ICML 2021 ; Part 7 of 16 (2022)

DEEP GENERALIZED METHOD OF MOMENTS FOR INSTRUMENTAL VARIABLE ANALYSIS

von Bennett, Andrew
Veröffentlicht in NeurIPS (33. : 2019 : Vancouver, British Columbia) 32nd Conference on Neural Information Processing Systems (NeurIPS 2019) ; Volume 5 of 20 (2020)

The power of optimization over randomization in designing experiments involving small samples

von Bertsimas, Dimitris
Veröffentlicht in Operations research (2015)

Inventory management in the era of big data

von Bertsimas, Dimitris
Veröffentlicht in Production and operations management (2016)

Control Variates for Slate Off-Policy Evaluation

von Vlassis, Nikos
Veröffentlicht in NeurIPS (35. : 2021 : Online) 35th Conference on Neural Information Processing Systems (NeurIPS 2021) ; Volume 5 of 36 (2022)

Doubly Robust Distributionally Robust Off-Policy Evaluation and Learning

von Kallus, Nathan
Veröffentlicht in International Conference on Machine Learning (39. : 2022 : Baltimore, Md.; Online) International Conference on Machine Learning (ICML 2022) ; Part 13 of 33 (2023)

Learning Bellman Complete Representations for Offline Policy Evaluation

von Chang, Jonathan
Veröffentlicht in International Conference on Machine Learning (39. : 2022 : Baltimore, Md.; Online) International Conference on Machine Learning (ICML 2022) ; Part 4 of 33 (2023)

Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems

von Uehara, Masatoshi
Veröffentlicht in NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 2 of 50 (2023)