DASH: Warm-Starting Neural Network Training in Stationary Settings without Loss of Plasticity.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
Provable Benefit of Cutout and CutMix for Feature Learning.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
Provable Benefit of Mixup for Finding Optimal Decision Boundaries.
Proceedings of the International Conference on Machine Learning, 2023