80 citations · 343 across the 26 of their papers we have counts for
6 papers · 2 filters
Incremental Learning via Rate Reduction
Ziyang Wu, Christina Baek, Chong You +1
Current deep learning architectures suffer from catastrophic forgetting, a failure to retain knowledge of previously learned classes when incrementally trained on new classes. The…
Deep Networks from the Principle of Rate Reduction
Kwan Ho Ryan Chan, Yaodong Yu, Chong You +3
This work attempts to interpret modern deep (convolutional) networks from the principles of rate reduction and (shift) invariant classification. We show that the basic iterative gr…
Adversarial Robustness of Stabilized NeuralODEs Might be from Obfuscated Gradients
Yifei Huang, Yaodong Yu, Hongyang Zhang +2
In this paper we introduce a provably stable architecture for Neural Ordinary Differential Equations (ODEs) which achieves non-trivial adversarial robustness under white-box advers…
Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization
Chong You, Zhihui Zhu, Qing Qu +1
Recent advances have shown that implicit bias of gradient descent on over-parameterized models enables the recovery of low-rank matrices from linear measurements, even with no prio…
Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction
Yaodong Yu, Kwan Ho Ryan Chan, Chong You +2
To learn intrinsic low-dimensional structures from high-dimensional data that most discriminate between classes, we propose the principle of Maximal Coding Rate Reduction ($\text{M…
Rethinking Bias-Variance Trade-off for Generalization of Neural Networks
Zitong Yang, Yaodong Yu, Chong You +2
The classical bias-variance trade-off predicts that bias decreases and variance increase with model complexity, leading to a U-shaped risk curve. Recent work calls this into questi…