Publications
Selected publications and publicly available preprints are listed below. For the latest list, see Google Scholar.
2026
Journal Articles
- Asymptotically Optimal Change Detection for Unnormalized Pre- and Post-Change Distributions. Sequential Analysis, 45(2):321–346, 2026. arXiv.
Conference Papers
- Convergence of Byzantine-Resilient Gradient Tracking via Probabilistic Edge Dropout. IEEE Conference on Decision and Control (CDC), 2026. Accepted; to appear.
- Cascading Robustness Verification: Toward Efficient Model-Agnostic Certification. IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), 2026. Conference program.
Preprints
- A Mixture-of-Experts Framework for Multi-Stream Quickest Change Detection. arXiv:2610.20876, 2026.
- Certified Robustness via Sparse Second-Order Cone Relaxations. arXiv:2610.16016, 2026.
- Quickest Change Detection with Diffusion-Integrated Scores. arXiv:2610.12200, 2026.
- Nash Equilibrium Text: A Game-Theoretic Decoding Framework for Text Generation. arXiv:2610.05817, 2026.
- Transformers as In-Context Samplers: From Closed-Form Diffusion to Estimation-Free Sampling. arXiv:2609.08981, 2026.
- Tight Sample Bounds for Rényi and Min-Entropy Estimation. arXiv:2607.16966, 2026.
2024
- Min-Max Optimization under Delays. American Control Conference (ACC), 2024.
- Finite-Time Analysis of Asynchronous Multi-Agent TD Learning. American Control Conference (ACC), 2024.
- DASA: Delay-Adaptive Multi-Agent Stochastic Approximation. IEEE Conference on Decision and Control (CDC), 2024.
- Stochastic Approximation with Delayed Updates: Finite-Time Rates under Markovian Sampling. International Conference on Artificial Intelligence and Statistics (AISTATS), 2024.
2023
- Discrete and Continuous Optimization for Collaborative and Multi-Task Learning. Ph.D. thesis, University of Pennsylvania, 2023.
- Score-Based Methods for Discrete Optimization in Deep Learning. 2023.
2022
- Collaborative Linear Bandits with Adversarial Agents: Near-Optimal Regret Bounds. Advances in Neural Information Processing Systems (NeurIPS), 2022.
- Distributed Statistical Min-Max Learning in the Presence of Byzantine Agents. IEEE Conference on Decision and Control (CDC), 2022.
- Minimax Optimization: The Case of Convex-Submodular. International Conference on Artificial Intelligence and Statistics (AISTATS), 2022. Oral presentation.
2021
- Optimal Algorithms for Submodular Maximization with Distributed Constraints. Learning for Dynamics and Control (L4DC), 2021.
2020
- Submodular Meta-Learning. Advances in Neural Information Processing Systems (NeurIPS), 2020.
2019
- Max-Min Fairness Design in MIMO Interference Channels: A Minorization–Maximization Approach. IEEE Transactions on Signal Processing (TSP), 2019.