1 citations · 1 across the 6 of their papers we have counts for
6 papers
Lower Bounds for Nonconvex-PŁ Minimax Optimization
Siyu Pan, Jiajin Li
We study the deterministic first-order oracle complexity of finding stationary points of the value function in smooth nonconvex-Polyak-Łojasiewicz (NC-PŁ) minimax optimization. We…
Optimal Deterministic Oracle Complexity for Weakly Convex Optimization
Jiajin Li, Siyu Pan
We study the oracle complexity of finding -stationary points of -weakly convex and -Lipschitz functions, where stationarity is measured by the gradient of the Moreau envel…
Smoothing Meets Perturbation: Unified and Tight Analysis for Nonconvex-Concave Minimax Optimization
Jiajin Li, Mahesh Nagarajan, Siyu Pan +1
This paper studies smooth nonconvex-concave minimax optimization and two acceleration mechanisms for single-loop first-order methods: dual perturbation and smoothing. Although both…
Stability Evaluation via Distributional Perturbation Analysis
Jose Blanchet, Peng Cui, Jiajin Li +1
The performance of learning models often deteriorates when deployed in out-of-sample environments. To ensure reliable deployment, we propose a stability evaluation criterion based…
Automatic Outlier Rectification via Optimal Transport
Jose Blanchet, Jiajin Li, Markus Pelger +1
In this paper, we propose a novel conceptual framework to detect outliers using optimal transport with a concave cost function. Conventional outlier detection approaches typically…
Distributionally Robust Optimization and Robust Statistics
Jose Blanchet, Jiajin Li, Sirui Lin +1
We review distributionally robust optimization (DRO), a principled approach for constructing statistical estimators that hedge against the impact of deviations in the expected loss…