← Optimization & Theory
Deep Learning › Optimization & Theory ›

Theory

1072 directly classified papers

Papers per year

Papers

The Neural Covariance SDE: Shaped Infinite Depth-and-Width Networks at Initialization NIPS 2022
ExSum: From Local Explanations to Model Understanding NAACL 2022
Topology-aware Generalization of Decentralized SGD ICML 2022
On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features ICML 2022
Uncertainty Modeling in Generative Compressed Sensing ICML 2022
Neural Network Weights Do Not Converge to Stationary Points: An Invariant Measure Perspective ICML 2022
Informed Learning by Wide Neural Networks: Convergence, Generalization and Sampling Complexity ICML 2022
Does the Data Induce Capacity Control in Deep Learning? ICML 2022
Locally Sparse Neural Networks for Tabular Biomedical Data ICML 2022
Synergy and Symmetry in Deep Learning: Interactions between the Data, Model, and Inference Algorithm ICML 2022
DAVINZ: Data Valuation using Deep Neural Networks at Initialization ICML 2022
More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize ICML 2022
On the Implicit Bias of Gradient Descent for Temporal Extrapolation AISTATS 2022
On Non-Linear operators for Geometric Deep Learning NIPS 2022
Three-stage Evolution and Fast Equilibrium for SGD with Non-degerate Critical Points ICML 2022
Extended Unconstrained Features Model for Exploring Deep Neural Collapse ICML 2022
Fully-Connected Network on Noncompact Symmetric Space and Ridgelet Transform based on Helgason-Fourier Analysis ICML 2022
Reverse Engineering the Neural Tangent Kernel ICML 2022
Convex Analysis of the Mean Field Langevin Dynamics AISTATS 2022
Deep Network Approximation in Terms of Intrinsic Parameters ICML 2022
Neural Tangent Kernel Beyond the Infinite-Width Limit: Effects of Depth and Initialization ICML 2022
Convergence Rates of Non-Convex Stochastic Gradient Descent Under a Generic Lojasiewicz Condition and Local Smoothness ICML 2022
The Neural Race Reduction: Dynamics of Abstraction in Gated Networks ICML 2022
Vanishing Curvature in Randomly Initialized Deep ReLU Networks AISTATS 2022
Towards Theoretical Analysis of Transformation Complexity of ReLU DNNs ICML 2022