A Single-Loop, Constant-Batch First-Order Penalty Method for Stochastic Bilevel Optimization
math.OC, cs.LG
Submitted: 2026-10-05
Updated: 2026-10-05
Sources
- Self-Guided Noise-Free Data Generation for Efficient Zero-Shot Learning
- Approximation Methods for Bilevel Programming
- Randomized Stochastic Variance-Reduced Methods for Multi-Task Stochastic Bilevel Optimization
- On the Complexity of First-Order Methods in Stochastic Bilevel Optimization
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
Related papers
- Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise
- Adam-HNAG: A Convergent Reformulation of Adam with Accelerated Rate
- Incremental Learning in Mirror Flows
- Second-Order Optimization with Asynchronous Curvature
- Online Control via Counterfactual Tracking
- Asynchronous Replanning in Two Population Linear Quadratic Mean Field Games: Information Requirements and Stability