DynaMS: Dyanmic Margin Selection for Efficient Deep Learning.
Proceedings of the Eleventh International Conference on Learning Representations, 2023
Understanding and Quantifying Adversarial Examples Existence in Linear Classification.
Proceedings of the International Conference on Machine Learning and Cybernetics, 2022
Finding Dynamics Preserving Adversarial Winning Tickets.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022
Revisiting Parameter Sharing for Automatic Neural Channel Number Search.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020