← Optimization & Theory
Deep Learning › Optimization & Theory ›

Theory

1072 directly classified papers

Papers per year

Papers

Collegial Ensembles NIPS 2020
The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks NIPS 2020
Nonasymptotic Guarantees for Spiked Matrix Recovery with Generative Priors NIPS 2020
Finite Versus Infinite Neural Networks: an Empirical Study NIPS 2020
Adversarial Training is a Form of Data-dependent Operator Norm Regularization NIPS 2020
Reconciling Modern Deep Learning with Traditional Optimization Analyses: The Intrinsic Learning Rate NIPS 2020
Rational neural networks NIPS 2020
O(n) Connections are Expressive Enough: Universal Approximability of Sparse Transformers NIPS 2020
On Infinite-Width Hypernetworks NIPS 2020
Robustness Analysis of Non-Convex Stochastic Gradient Descent using Biased Expectations NIPS 2020
On the linearity of large non-linear models: when and why the tangent kernel is constant NIPS 2020
Assessing Local Generalization Capability in Deep Models AISTATS 2020
LSTM Neural Networks: Input to State Stability and Probabilistic Safety Verification L4DC 2020
Stable behaviour of infinitely wide deep neural networks AISTATS 2020
The phase diagram of approximation rates for deep neural networks NIPS 2020
Escaping Saddle-Point Faster under Interpolation-like Conditions NIPS 2020
Generalization error in high-dimensional perceptrons: Approaching Bayes error with convex optimization NIPS 2020
Counterexample-Guided Learning of Monotonic Neural Networks NIPS 2020
Universal Approximation with Deep Narrow Networks COLT 2020
Analytic Characterization of the Hessian in Shallow ReLU Models: A Tale of Symmetry NIPS 2020
A shooting formulation of deep learning NIPS 2020
In search of robust measures of generalization NIPS 2020
Understanding Double Descent Requires A Fine-Grained Bias-Variance Decomposition NIPS 2020
Sharp Representation Theorems for ReLU Networks with Precise Dependence on Depth NIPS 2020
Non-Euclidean Universal Approximation NIPS 2020