Wu-Jun Li

Optimizing Class Distribution in Memory for Multi-Label Online Continual Learning

2022 · arXiv (Cornell University)

Online continual learning, especially when task identities and task boundaries are unavailable, is a challenging continual learning setting. One representative kind of methods for online continual learning is replay-based methods, in which a replay buffer …

Ordered Local Momentum for Asynchronous Distributed Learning Under Arbitrary Delays

2026 · Proceedings of the AAAI Conference on Artificial Intelligence

Momentum SGD (MSGD) serves as a foundational optimizer in training deep models due to momentum's key role in accelerating convergence and enhancing generalization. Meanwhile, asynchronous distributed learning is crucial for training large-scale deep models, especially …