作者
Michael I. Jordan
Machine Learning
Operationalizing Counterfactual Metrics: Incentives, Ranking, and Information Asymmetry
Prediction-Powered Inference
Comments Code is available at https://github.com/aangelopoulos/ppi_py
Contract Design With Safety Inspections
Fine-Tuning Language Models with Advantage-Induced Policy Alignment
Class-Conditional Conformal Prediction with Many Classes
A Unifying Perspective on Multi-Calibration: Game Dynamics for Multi-Objective Learning
Comments 45 pages. Authors are ordered alphabetically
On Optimal Caching and Model Multiplexing for Large Model Inference
Nesterov Meets Optimism: Rate-Optimal Separable Minimax Optimization
Comments 44 pages. This version matches the camera-ready that appeared at ICML 2023 under the same title
Last-Iterate Convergence of Saddle-Point Optimizers via High-Resolution Differential Equations
Journal ref Minimax Theory 8, Number 2 (2023) 333--380
Scaff-PD: Communication Efficient Fair and Robust Federated Learning
Modeling Content Creator Incentives on Algorithm-Curated Platforms
Comments presented at ICLR 2023 (top 5%)
Optimization on manifolds: A symplectic approach
Comments additional results, including rates for constrained optimization on manifolds
Accelerating Inexact HyperGradient Descent for Bilevel Optimization
Evaluating and Incentivizing Diverse Data Contributions in Collaborative Learning
Federated Conformal Predictors for Distributed Uncertainty Quantification
Comments 23 pages, 18 figures, accepted to International Conference on Machine Learning (ICML 2023)
The Sample Complexity of Online Contract Design
Online Learning in a Creator Economy
Online Learning in Stackelberg Games with an Omniscient Follower
Byzantine-Robust Federated Learning with Optimal Statistical Rates and Privacy Guarantees
Evaluating Sensitivity to the Stick-Breaking Prior in Bayesian Nonparametrics (Rejoinder)
Comments Rejoinder for the discussion article "Evaluating Sensitivity to the Stick-Breaking Prior in Bayesian Nonparametrics'' in Bayesian Analysis
Finding Regularized Competitive Equilibria of Heterogeneous Agent Macroeconomic Models with Reinforcement Learning
Comments 44 pages
Solving Constrained Variational Inequalities via a First-order Interior Point-based Method
Journal ref International Conference on Learning Representations 2023, Kigali, Rwanda
A Statistical Analysis of Polyak-Ruppert Averaged Q-learning
Comments Accepted by AISTATS 2023
First-Order Algorithms for Nonlinear Generalized Nash Equilibrium Problems
Comments Accepted by Journal of Machine Learning Research; Add the references and the funding information; 44 pages, 1 table
Parallelizing Contextual Bandits
Learning Equilibria in Matching Markets from Bandit Feedback
Comments Accepted to the Journal of the ACM; conference version appeared at NeurIPS 2021
Competition, Alignment, and Equilibria in Digital Marketplaces
Comments To appear at AAAI 2023
Meta-Analysis of Randomized Experiments with Applications to Heavy-Tailed Response Data
Projection Robust Wasserstein Distance and Riemannian Optimization
Comments Accepted by NeurIPS 2020; The first two authors contributed equally; fix the confusing parts in the proof and refine the algorithms and complexity bounds
