← Optimization & Theory
Deep Learning › Optimization & Theory ›

Theory

1072 directly classified papers

Papers per year

Papers

Defending Against Adversarial Attacks via Neural Dynamic System NIPS 2022
Neural Network Architecture Beyond Width and Depth NIPS 2022
A PAC-Bayesian Generalization Bound for Equivariant Networks NIPS 2022
Size and depth of monotone neural networks: interpolation and approximation NIPS 2022
Sketching based Representations for Robust Image Classification with Provable Guarantees NIPS 2022
Transition to Linearity of General Neural Networks with Directed Acyclic Graph Architecture NIPS 2022
Chaotic Dynamics are Intrinsic to Neural Network Training with SGD NIPS 2022
How Powerful are K-hop Message Passing Graph Neural Networks NIPS 2022
The alignment property of SGD noise and how it helps select flat minima: A stability analysis NIPS 2022
Why Robust Generalization in Deep Learning is Difficult: Perspective of Expressive Power NIPS 2022
Your Transformer May Not be as Powerful as You Expect NIPS 2022
ExSum: From Local Explanations to Model Understanding NAACL 2022
On the Effectiveness of Iterative Learning Control L4DC 2022
Implicit Regularization with Polynomial Growth in Deep Tensor Factorization ICML 2022
Exploring the Gap between Collapsed & Whitened Features in Self-Supervised Learning ICML 2022
Sparse Double Descent: Where Network Pruning Aggravates Overfitting ICML 2022
Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees ICML 2022
Robustness Implies Generalization via Data-Dependent Generalization Bounds ICML 2022
Implicit Bias of Linear Equivariant Networks ICML 2022
Neural Tangent Kernel Analysis of Deep Narrow Neural Networks ICML 2022
Generalization Guarantee of Training Graph Convolutional Networks with Graph Topology Sampling ICML 2022
Hessian-Free High-Resolution Nesterov Acceleration For Sampling ICML 2022
Benefits of Overparameterized Convolutional Residual Networks: Function Approximation under Smoothness Constraint ICML 2022
Minimizing Control for Credit Assignment with Strong Feedback ICML 2022
A Dynamical System Perspective for Lipschitz Neural Networks ICML 2022