Papers were accepted by ICML 2026!

The following papers accepted by ICML 2026 (main conference and workshop). Congratulations to Kaoru and Haruka!

Kaoru Otsuka, Yuki Takezawa, Makoto Yamada Delyed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation, ICML 2026

Haruka Eshima and Makoto Yamada, Effects of width-dependent model hyperparameters and l_2-regularization on the loss landscape of two-layer ReLU networks, HiLD 2026: 4th Workshop on High-dimensional Learning Dynamics, ICML 2026