Michael I. Jordan

The Sample Complexity of Online Reinforcement Learning: A Multi-model Perspective

Online Decision-Focused Learning

Understanding In-context Learning of Addition via Activation Subspaces

Sample Complexity and Representation Ability of Test-time Scaling Paradigms

Locally Adaptive Multi-Objective Learning

How Do Transformers Perform Two-Hop Reasoning in Context?

Scalable Utility-Aware Multiclass Calibration

Valid Selection among Conformal Sets

Backward Conformal Prediction

Generalization or Hallucination? Understanding Out-of-Context Reasoning in Transformers

Statistical Collusion by Collectives on Learning Platforms

Conformal Prediction under Lévy-Prokhorov Distribution Shifts: Robustness to Local and Global Perturbations

Prediction-Aware Learning in Multi-Agent Systems

AutoEval Done Right: Using Synthetic Data for Model Evaluation