Kevin Tian

The Power of Iterative Filtering for Supervised Learning with (Heavy) Contamination

Private Geometric Median in Nearly-Linear Time

More of the Same: Persistent Representational Harms Under Increased Representation

Learning Noisy Halfspaces with a Margin: Massart is No Harder than Random

Semi-Random Matrix Completion via Flow-Based Adaptive Reweighting

Testing Calibration in Nearly-Linear Time

Private Stochastic Convex Optimization with Heavy Tails: Near-Optimality from Simple Reductions