Publications
Algorithmic Optimality Guarantees for Nonsmooth \(\mathcal{H}_{\infty }\) Output-Feedback Policy Search
IEEE Conference on Decision and Control (CDC), 2026
A Unified Framework for Statistical Testing of Invariance
ICML 2026 Workshop on Hypothesis Testing (HT @ ICML workshop), 2026
On Lipschitz Explosion in Deep Neural Networks with Normalization: Consequences for Optimization and Adversarial Robustness
High-dimensional Learning Dynamics (HiLD @ ICML workshop), 2026
Efficient Learning and Symmetry Discovery under Exact Invariances
Annual Conference on Learning Theory 2026 (COLT), 2026
From Finite to Infinite Groups: A Polynomial-Time Algorithm for Learning with Exact Invariances
Symmetry and Geometry in Neural Representations (NeuReps @ NeurIPS workshop), 2025 (Oral Presentation)
Data Generation without Function Estimation
Optimization for Machine Learning (OPT @ NeurIPS workshop), 2025 (Oral Presentation)
Dynamics at the Frontiers of Optimization, Sampling, and Games (DynaFront @ NeurIPS workshop), 2025
Dynamics at the Frontiers of Optimization, Sampling, and Games (DynaFront @ NeurIPS workshop), 2025
Cautious Optimism: A Meta-Algorithm for Near-Constant Regret in General Games
Twenty-Sixth ACM Conference on Economics and Computation (EC), 2025
Faster Rates for No-Regret Learning in General Games via Cautious Optimism
The Annual ACM Symposium on Theory of Computing (STOC), 2025
Learning with Exact Invariances in Polynomial Time
International Conference on Machine Learning (ICML), 2025 (Spotlight Presentation - Top 2.6% of Submissions)
Conference on Parsimony and Learning (CPAL), Recent Spotlight Track, 2025
Conference on Parsimony and Learning (CPAL), Recent Spotlight Track, 2025
A Robust Kernel Statistical Test of Invariance: Detecting Subtle Asymmetries
International Conference on Artificial Intelligence and Statistics (AISTAT), 2025 (Oral Presentation - Top 2% of Submissions)
Conference on Parsimony and Learning (CPAL), Recent Spotlight Track, 2025
Conference on Parsimony and Learning (CPAL), Recent Spotlight Track, 2025
Learning Decision Policies with Instrumental Variables through Double Machine Learning
International Conference on Machine Learning (ICML), 2024
International Conference on Machine Learning (ICML), 2024
High-dimensional Learning Dynamics: The Emergence of Structure and Reasoning (HiLD @ ICML workshop), 2024 (Best Paper Award)
High-dimensional Learning Dynamics: The Emergence of Structure and Reasoning (HiLD @ ICML workshop), 2024 (Best Paper Award)
Double Machine Learning Based Structure Identification from Temporal Data
Transactions on Machine Learning Research (TMLR), 2025
On Scale-Invariant Sharpness Measures
Mathematics of Modern Machine Learning (M3L @ NeurIPS workshop), 2023
DRCFS: Doubly Robust Causal Feature Selection
International Conference on Machine Learning (ICML), 2023
Causal Feature Selection via Orthogonal Search
Transactions on Machine Learning Research (TMLR), 2022
Pyfectious: A probabilistic hierarchical simulator of infectious diseases and fine-grained control measures
PLOS Computational Biology 19(1): e1010799, 2023
GeneDisco: A Benchmark for Experimental Design in Drug Discovery
International Conference on Learning Representations (ICLR), 2022
Adaptive Experimental Design and Active Learning in the Real World (ReALML @ ICML workshop), 2022 (Spotlight Presentation)
Adaptive Experimental Design and Active Learning in the Real World (ReALML @ ICML workshop), 2022 (Spotlight Presentation)
Preprints and submissions
Breaking the 1/3 Barrier for Approximate Nash Equilibria in Symmetric Bimatrix Games
Submitted (under review)
Settling the Support Complexity of Correlated Equilibria
Submitted (under review)
Spontaneous Symmetry Breaking via Regularized Optimization: Hardness and Approximation
Submitted (under review)
Exact-Form Regret and Conservative Correlated Equilibria
Submitted (under review)
Tropical Gaussian Anticoncentration: Settling Optimal Instance-Dependent Bounds for Online Learning in Extensive-Form Games
Submitted (under review)
Homological Barriers to Stable Local Nash Dynamics in Quadratic Zero-Sum Games
Submitted (under review)
Resolvent Ellipsoid for Minty Set Inclusions
Submitted (under review)
Coverage Paths: A Selection-Safe Interface for Online Conformal Prediction
Submitted (under review)
Double Machine Learning for Conditional Moment Restrictions: IV regression, Proximal Causal Learning and Beyond
arXiv:2506.14950, 2025
Physical Derivatives: Computing policy gradients by physical forward-propagation
arXiv:2201.05830, 2022
* denotes equal contributions.