Publications

Google Scholar link

Selected Publications

• Margin Maximization in Attention Mechanism, NeurIPS spotlight (~3% acceptance), 2023
• FedNest: Federated Bilevel, Minimax, and Compositional Optimization, ICML oral (~2% acceptance), 2022
• Revisiting Ho-Kalman based system identification: robustness and finite-sample analysis, IEEE TAC 2021
• Label-Imbalanced and Group-Sensitive Classification under Overparameterization, NeurIPS 2021
• Generalization Guarantees for Neural Architecture Search with Train-Validation Split, ICML 2021
• Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks, AAAI 2021
• Towards moderate overparameterization: global convergence guarantees for training shallow neural networks, IEEE Journal on Selected Areas in Information Theory 2020
• Gradient descent with early stopping is provably robust to label noise for overparameterized neural networks, AISTATS 2020
• Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?, ICML 2019
• Sharp time-data tradeoffs for linear inverse problems, Transactions on Information Theory 2018
• Universality laws for randomized dimension reduction, with applications, Information & Inference 2018
• Regularized linear regression: A precise analysis of the estimation error, COLT 2015
• Simultaneously structured models with application to sparse and low-rank matrices, Transactions on Information Theory 2015
• The squared-error of generalized LASSO: A precise analysis, Allerton 2013