Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Accelerating LMO-Based Optimization via Implicit Gradient Transport
Won-Jun Jang, Si-Hyeon Lee
Recent optimizers such as Lion and Muon have demonstrated strong empirical performance by normalizing gradient momentum via linear minimization oracles (LMOs). While variance reduc…
cs.LG2025
Provably Near-Optimal Federated Ensemble Distillation with Negligible Overhead
Won-Jun Jang, Hyeon-Seo Park, Si-Hyeon Lee
Federated ensemble distillation addresses client heterogeneity by generating pseudo-labels for an unlabeled server dataset based on client predictions and training the server model…