Provides the first systematic generalization analysis via algorithmic stability for single-timescale and two-timescale stochastic gradient descent-ascent in bilevel minimax problems.
Mathematical Programming , volume=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Robust learning problems are formulated as quasar-convex optimization, and HiPPA is proposed as an inexact high-order proximal method with global and superlinear convergence guarantees.
The paper motivates stochastic optimization problems from statistical perspectives and describes offline and online approaches to solve expectation minimization problems.
citing papers explorer
-
On the Stability and Generalization of First-order Bilevel Minimax Optimization
Provides the first systematic generalization analysis via algorithmic stability for single-timescale and two-timescale stochastic gradient descent-ascent in bilevel minimax problems.
-
Robust Learning Meets Quasar-Convex Optimization: Inexact High-Order Proximal-Point Methods
Robust learning problems are formulated as quasar-convex optimization, and HiPPA is proposed as an inexact high-order proximal method with global and superlinear convergence guarantees.
-
Stochastic Optimization and Data Science
The paper motivates stochastic optimization problems from statistical perspectives and describes offline and online approaches to solve expectation minimization problems.