2 papers
cs.LG2026
NBCLT: Parameter-Agnostic Norm-Ball Clipped Local Training
Linxuan Pan, Shucheng Yang, Junchi Yang
Distributed learning with multiple local steps reduces communication but aggravates drift, and its practical performance often depends on carefully tuned hyperparameters under hete…
math.OC2026
Optimal High-Order Methods for Solving Monotone Variational Inequalities
Xinliang Zhang, Lesi Chen, Linxuan Pan +3
We study second- and higher-order methods for solving smooth monotone variational inequalities (MVI). Monteiro and Svaiter (SIAM J. Optim., 2012) showed that a second-order method,…