Publications (Google Scholar, dblp, Semantic Scholar)
- A Sub-Quadratic Time Algorithm for Robust Sparse Mean Estimation International Conference on Machine Learning (ICML), 2024 (Spotlight) [Abstract] [arXiv] [Conference version] [Slides (of a survey; 1hr)]
- The Sample Complexity of Simple Binary Hypothesis Testing Conference on Learning Theory (COLT), 2024 [Abstract] [arXiv] [Conference version] [Slides (10min)]
- Simple Binary Hypothesis Testing under Local Differential Privacy and Communication Constraints IEEE Transactions on Information Theory (Trans. Inf. Theory), 2024 An extended abstract appeared at Conference on Learning Theory (COLT), 2023 [Abstract] [arXiv] [Journal version] [Slides (20min)] [Slides (1hr)] [Code]
- Black-Box $k$-to-1-PCA Reductions: Theory and Applications Conference on Learning Theory (COLT), 2024 [Abstract] [arXiv] [Conference version] [Slides (10min)]
- Robust Sparse Estimation for Gaussians with Optimal Error under Huber Contamination International Conference on Machine Learning (ICML), 2024 [Abstract] [arXiv] [Conference version]
- Semi-supervised Group DRO: Combating Sparsity with Unlabeled Data International Conference on Algorithmic Learning Theory (ALT), 2024 [Abstract] [Conference version]
- Robust regression with covariate filtering: Heavy tails and adversarial contamination Journal of the American Statistical Association (JASA), 2024 [Abstract] [arXiv] [Journal version] [Code]
- Communication-constrained hypothesis testing: Optimality, robustness, and reverse data processing inequalities IEEE Transactions on Information Theory (Trans. Inf. Theory), 2024 A shorter version appeared at ISIT 2022 [Abstract] [arXiv] [Journal version]
- Near-Optimal Algorithms for Gaussians with Huber Contamination: Mean Estimation and Linear Regression Advances in Neural Information Processing Systems (NeurIPS), 2023 [Abstract] [arXiv] [Conference version]
- A Spectral Algorithm for List-Decodable Covariance Estimation in Relative Frobenius Norm Advances in Neural Information Processing Systems (NeurIPS), 2023 (Spotlight) [Abstract] [arXiv] [Conference version]
- Nearly-Linear Time and Streaming Algorithms for Outlier-Robust PCA International Conference on Machine Learning (ICML), 2023 [Abstract] [arXiv] [Conference version]
- Gaussian Mean Testing Made Simple SIAM Symposium on Simplicity in Algorithms (SOSA), 2023 [Abstract] [arXiv] [Conference version]
- Outlier-Robust Sparse Mean Estimation for Heavy-Tailed Distributions Advances in Neural Information Processing Systems (NeurIPS), 2022 [Abstract] [arXiv] [Conference version]
- List-Decodable Sparse Mean Estimation via Difference-of-Pairs Filtering Advances in Neural Information Processing Systems (NeurIPS), 2022 (Oral) [Abstract] [arXiv] [Conference version]
- Robust Sparse Mean Estimation via Sum of Squares Conference on Learning Theory (COLT), 2022 [Abstract] [arXiv] [Conference version]
- Streaming Algorithms for High-Dimensional Robust Statistics International Conference on Machine Learning (ICML), 2022 [Abstract] [arXiv] [Conference version]
- Sharp Concentration Inequalities for the Centered Relative Entropy Information and Inference: a Journal of the IMA, 2022 [Abstract] [arXiv] [Journal version]
- Statistical Query Lower Bounds for List-Decodable Linear Regression Advances in Neural Information Processing Systems (NeurIPS), 2021 (Spotlight) [Abstract] [arXiv] [Conference version]
- Estimating location parameters in sample-heterogeneous distributions Information and Inference: a Journal of the IMA, 2021 A shorter version of this article appeared at ISIT 2019 [Abstract] [arXiv] [Journal version] [PDF]
- Outlier Robust Mean Estimation with Subgaussian Rates via Stability Advances in Neural Information Processing Systems (NeurIPS), 2020 [Abstract] [arXiv] [Conference version]
- Optimal Lottery Tickets via SubsetSum: Logarithmic Over-Parameterization is Sufficient Advances in Neural Information Processing Systems (NeurIPS), 2020 (Spotlight) [Abstract] [arXiv] [Conference version]
- Extracting robust and accurate features via a robust information bottleneck IEEE Journal on Selected Areas in Information Theory (JSAIT), 2020 [Abstract] [Journal version] [PDF]
- Deep Topic Models for Multi-label Learning International Conference on Artificial Intelligence and Statistics (AISTATS), 2019 [Abstract] [Conference version]
- Generalization Error Bounds for Noisy, Iterative Algorithms IEEE International Symposium on Information Theory (ISIT), 2018 [Abstract] [arXiv] [Conference version]