Ilias Diakonikolas

Full Professor@University of Wisconsin-Madison·美国·OpenReview

研究方向

PAC Learning · Hypothesis Testing · Non-Parametric Estimation · Robust Statistics · Theoretical Machine Learning · Adversarial Robustness · Theory of Neural Networks

Ilias Diakonikolas

Replicable Distribution Testing

Algorithms and SQ Lower Bounds for Robustly Learning Real-valued Multi-Index Models

Statistical Query Hardness of Multiclass Linear Classification with Random Classification Noise

On Learning Parallel Pancakes with Mostly Uniform Weights

Robustly Learning Monotone Single-Index Models

Robust Regression of General ReLUs with Queries

Information-Computation Tradeoffs for Noiseless Linear Regression with Oblivious Contamination

Efficient Multivariate Robust Mean Estimation Under Mean-Shift Contamination

Batch List-Decodable Linear Regression via Higher Moments

On Fine-Grained Distinct Element Estimation

Online Linear Classification with Massart Noise

Reliable Learning of Halfspaces under Gaussian Marginals

A Near-optimal Algorithm for Learning Margin Halfspaces with Massart Noise

How Does Unlabeled Data Provably Help Out-of-Distribution Detection?

Active Learning of General Halfspaces: Label Queries vs Membership Queries

Learning a Single Neuron Robustly to Distributional Shifts and Adversarial Label Noise

Sample and Computationally Efficient Robust Learning of Gaussian Single-Index Models