← Optimization & Theory
Deep Learning › Optimization & Theory ›

Theory

1072 directly classified papers

Papers per year

Papers

Training deep residual networks for uniform approximation guarantees L4DC 2021
The Spectrum of Fisher Information of Deep Networks Achieving Dynamical Isometry AISTATS 2021
Regularization Matters: A Nonparametric Perspective on Overparametrized Neural Network AISTATS 2021
Learning with Gradient Descent and Weakly Convex Losses AISTATS 2021
A Dynamical View on Optimization Algorithms of Overparameterized Neural Networks AISTATS 2021
Outside Computation with Superior Functions NAACL 2021
Parametric Complexity Bounds for Approximating PDEs with Neural Networks NIPS 2021
On Learnability via Gradient Method for Two-Layer ReLU Neural Networks in Teacher-Student Setting ICML 2021
Dropout: Explicit Forms and Capacity Control ICML 2021
On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent ICML 2021
Uniform Convergence, Adversarial Spheres and a Simple Remedy ICML 2021
The Hintons in your Neural Network: a Quantum Field Theory View of Deep Learning ICML 2021
SPADE: A Spectral Method for Black-Box Adversarial Robustness Evaluation ICML 2021
Adversarial Robustness Guarantees for Random Deep Neural Networks ICML 2021
Toward Better Generalization Bounds with Locally Elastic Stability ICML 2021
Attention is not all you need: pure attention loses rank doubly exponentially with depth ICML 2021
Global Optimality Beyond Two Layers: Training Deep ReLU Networks via Convex Programs ICML 2021
Multiplicative Noise and Heavy Tails in Stochastic Optimization ICML 2021
Learning Curves for Analysis of Deep Networks ICML 2021
On the Random Conjugate Kernel and Neural Tangent Kernel ICML 2021
Characterizing Structural Regularities of Labeled Data in Overparameterized Models ICML 2021
Provable Lipschitz Certification for Generative Models ICML 2021
On the Generalization Power of Overfitted Two-Layer Neural Tangent Kernel Models ICML 2021
The Lipschitz Constant of Self-Attention ICML 2021
Representational aspects of depth and conditioning in normalizing flows ICML 2021