01
Menu
Preprints & Working Papers
10Details ↗
02
Optimal Deterministic Oracle Complexity for Weakly Convex Optimization
Preprint03
Nonconvex Composite Functional Constraints via First-Order Augmented Lagrangian Methods under Local Regularity
Preprint04
Spend Less, Reason Better: Budget-Aware Value Tree Search for LLM Agents
Preprint05
On the Width Scaling of Neural Optimizers under Matrix Operator Norms I: Row/Column Normalization and Hyperparameter Transfer
Preprint06
Doubly Smoothed Optimistic Gradients: A Universal Approach for Smooth Minimax Problems
Preprint07
Last-Iterate Convergence of Single-Loop Stochastic Methods for Constrained Convex-Concave Minimax Problems
PreprintUnder Review08
Smoothing Meets Perturbation: Unified and Tight Analysis for Nonconvex-Concave Minimax Optimization
PreprintUnder Review09
Spurious Stationarity and Hardness Results for Bregman Proximal-Type Algorithms
Preliminary version at OPT 2024Under Review10
Unifying Distributionally Robust Optimization via Optimal Transport with Conditional Moment Constraints
Under RevisionJournal Articles
401
Nonsmooth Nonconvex-Nonconcave Minimax Optimization: Primal-Dual Balancing and Iteration Complexity Analysis
Mathematical Programming, Series A02
Distributionally Robust Optimization and Robust Statistics
Statistical Science03
A Splitting Scheme for Flip-Free Distortion Energies
SIAM Journal on Imaging Sciences04
Understanding Notions of Stationarity in Nonsmooth Optimization
IEEE Signal Processing MagazineConference Papers
1401
Set Smoothness Unlocks Clarke Hyper-Stationarity in Bilevel Optimization
NeurIPSSpotlight02
Automatic Outlier Rectification via Optimal Transport
NeurIPS03
Stability Evaluation through Distributional Perturbation Analysis
ICML04
Synthetic Principal Component Design: Fast Covariate Balancing with Synthetic Controls
UAIOral05
Universal Gradient Descent Ascent Method for Nonconvex-Nonconcave Minimax Optimization
NeurIPS06
Outlier-Robust Gromov-Wasserstein for Graph Data
NeurIPSSpotlight07
A Convergent Single-Loop Algorithm for Relaxation of Gromov-Wasserstein in Graph Data
ICLR08
Tikhonov Regularization is Optimal Transport Robust under Martingale Constraints
NeurIPS09
Rethinking Graph Neural Networks for Anomaly Detection
ICML10
Modified Frank Wolfe in Probability Space
NeurIPS11
Deconvolutional Networks on Graph Data
NeurIPS12
Fast Epigraphical Projection-based Incremental Algorithms for Wasserstein Distributionally Robust SVM
NeurIPS13
The Gambler’s Problem and Beyond
ICLR14