Michael I. Jordan

On Identifying and Mitigating Bias in the Estimation of the COVID-19 Case Fatality Rate

Anastasios Nikolas Angelopoulos, Reese Pathak, Rohit Varma, Michael I. Jordan

Comments Harvard Data Science Review (2020) article available at https://hdsr.mitpress.mit.edu/pub/y9vc2u36

Journal ref Harvard Data Science Review, (Special Issue 1). 2021

Optimal variance-reduced stochastic approximation in Banach spaces

Wenlong Mou, Koulik Khamaru, Martin J. Wainwright, Peter L. Bartlett, Michael I. Jordan

Monotone Inclusions, Acceleration and Closed-Loop Control

Tianyi Lin, Michael. I. Jordan

Comments Accepted by Mathematics of Operations Research; 42 Pages

On the Complexity of Deterministic Nonsmooth and Nonconvex Optimization

Michael I. Jordan, Tianyi Lin, Manolis Zampetakis

Comments 28 Pages; Fix an error and add relevant references

Off-Policy Evaluation with Policy-Dependent Optimization Response

Wenshuo Guo, Michael I. Jordan, Angela Zhou

Comments Proceeding of the 2022 Conference on Neural Information Processing Systems

Gradient-Free Methods for Deterministic and Stochastic Nonsmooth Nonconvex Optimization

Tianyi Lin, Zeyu Zheng, Michael I. Jordan

Comments Accepted by NeurIPS 2022; 32 pages, 18 figures; Fix a confusing part in the proof of Theorem 3.1: we use Bertsekas [1973, Proposition 2.3] rather than Bertsekas [1973, Proposition 2.4] here and do not assume the convexity of the function f

TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels

Yaodong Yu, Alexander Wei, Sai Praneeth Karimireddy, Yi Ma, Michael I. Jordan

Comments Accepted at Neural Information Processing Systems (NeurIPS) 2022. V2 releases code

An Instance-Dependent Analysis for the Cooperative Multi-Player Multi-Armed Bandit

Aldo Pacchiano, Peter Bartlett, Michael I. Jordan

Comments 50 pages

A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning

Zixiang Chen, Chris Junchi Li, Angela Yuan, Quanquan Gu, Michael I. Jordan

Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control

Anastasios N. Angelopoulos, Stephen Bates, Emmanuel J. Candès, Michael I. Jordan, Lihua Lei

Comments Code available at https://github.com/aangelopoulos/ltt

First-Order Algorithms for Min-Max Optimization in Geodesic Metric Spaces

Michael I. Jordan, Tianyi Lin, Emmanouil-Vasileios Vlatakis-Gkaragkounis

Comments 39 pages, 12 figures, under submission

Uncertainty Sets for Image Classifiers using Conformal Prediction

Anastasios Angelopoulos, Stephen Bates, Jitendra Malik, Michael I. Jordan

Comments ICLR 2021 Spotlight, https://openreview.net/forum?id=eNdiU_DbM9 . Project website at https://people.eecs.berkeley.edu/~angelopoulos/blog/posts/conformal-classification/ . Codebase at https://github.com/aangelopoulos/conformal_classification

On the Theory of Reinforcement Learning with Once-per-Episode Feedback

Niladri S. Chatterji, Aldo Pacchiano, Peter L. Bartlett, Michael I. Jordan

Comments Published at NeurIPS 2022

A Diffusion Process Perspective on Posterior Contraction Rates for Parameters

Wenlong Mou, Nhat Ho, Martin J. Wainwright, Peter Bartlett, Michael I. Jordan

Comments 81 pages

Optimal Extragradient-Based Bilinearly-Coupled Saddle-Point Optimization

Simon S. Du, Gauthier Gidel, Michael I. Jordan, Chris Junchi Li

Comments More polishing and clarifications; 36 pages

Learning Two-Player Mixture Markov Games: Kernel Function Approximation and Correlated Equilibrium

Chris Junchi Li, Dongruo Zhou, Quanquan Gu, Michael I. Jordan

Comments 42 pages

Geometric Methods for Sampling, Optimisation, Inference and Adaptive Agents

Alessandro Barp, Lancelot Da Costa, Guilherme França, Karl Friston, Mark Girolami, Michael I. Jordan, Grigorios A. Pavliotis

Comments 30 pages, 4 figures; 42 pages including table of contents and references

Journal ref Handbook of Statistics, vol. 46, pp. 21--78 (2022)

Breaking Feedback Loops in Recommender Systems with Causal Inference

Karl Krauth, Yixin Wang, Michael I. Jordan

Continuous-time Analysis for Variational Inequalities: An Overview and Desiderata

Tatjana Chavdarova, Ya-Ping Hsieh, Michael I. Jordan

Ranking and Tuning Pre-trained Models: A New Paradigm for Exploiting Model Hubs

Kaichao You, Yong Liu, Ziyang Zhang, Jianmin Wang, Michael I. Jordan, Mingsheng Long

Comments 47 pages, camera-ready version for JMLR 2022

NumS: Scalable Array Programming for the Cloud

Melih Elibol, Vinamra Benara, Samyu Yagati, Lianmin Zheng, Alvin Cheung, Michael I. Jordan, Ion Stoica

Mechanisms that Incentivize Data Sharing in Federated Learning

Sai Praneeth Karimireddy, Wenshuo Guo, Michael I. Jordan

No-Regret Learning in Partially-Informed Auctions

Wenshuo Guo, Michael I. Jordan, Ellen Vitercik

Comments 30 pages

Recommendation Systems with Distribution-Free Reliability Guarantees

Anastasios N. Angelopoulos, Karl Krauth, Stephen Bates, Yixin Wang, Michael I. Jordan

Sampling Can Be Faster Than Optimization

Yi-An Ma, Yuansi Chen, Chi Jin, Nicolas Flammarion, Michael I. Jordan

A Variational Perspective on Accelerated Methods in Optimization

Andre Wibisono, Ashia C. Wilson, Michael I. Jordan

Comments 38 pages. Subsumes an earlier working draft arXiv:1509.03616

Robust Calibration with Multi-domain Temperature Scaling

Yaodong Yu, Stephen Bates, Yi Ma, Michael I. Jordan

Fixed-Support Wasserstein Barycenters: Computational Hardness and Fast Algorithm

Tianyi Lin, Nhat Ho, Xi Chen, Marco Cuturi, Michael I. Jordan

Comments Accepted by NeurIPS 2020; fix some confusing parts in the proof and improve the empirical evaluation

Online Nonsubmodular Minimization with Delayed Costs: From Full Information to Bandit Feedback

Tianyi Lin, Aldo Pacchiano, Yaodong Yu, Michael I. Jordan

Comments Accepted by ICML 2022; The first three authors contributed equally to this work; 36 pages, 9 figures

Taming Nonconvexity in Kernel Feature Selection -- Favorable Properties of the Laplace Kernel

Feng Ruan, Keli Liu, Michael I. Jordan

Comments 26 pages main text; 74 pages total; appendix rewritten (typo fixed; proof structure reorganized)