Statistical Learning
Certified Robustness via Dynamic Margin Maximization and Improved Lipschitz Regularization
To improve the robustness of deep classifiers against adversarial perturbations, many approaches have been proposed, such as designing new architectures with better robustness properties (e.g., Lipschitz-capped networks), or modifying the
Chaining Mutual Information and Tightening Generalization Bounds
Amir Asadi, Emmanuel Abbe, Sergio Verdu
Neural Information Processing Systems http://nips.cc/
Multi-view Masked Contrastive Representation Learning for Endoscopic Video Analysis
Specifically, we propose a multi-view masking strategy for addressing the challenges of endoscopic videos.
Boosted Sparse and Low-Rank Tensor Regression
Lifang He, Kun Chen, Wanwan Xu, Jiayu Zhou, Fei Wang
Neural Information Processing Systems http://nips.cc/
A Communication Efficient Stochastic Multi-Block Alternating Direction Method of Multipliers
Neural Information Processing Systems http://nips.cc/
Ease-of-Teaching and Language Structure from Emergent Communication
Some leveloflanguage structure (e.g., compositionality) has been found in the learned communication protocols.
5598cf1b2905a26ddb863e6705588327-Paper-Conference.pdf
Video understanding relies on accurate action detection for temporal analysis.
