← Optimization & Theory
Deep Learning › Optimization & Theory ›

Theory

1072 directly classified papers

Papers per year

Papers

Synthetic data for model selection ICML 2023
Gradient Descent in Neural Networks as Sequential Learning in Reproducing Kernel Banach Space ICML 2023
Fundamental Limits of Two-layer Autoencoders, and Achieving Them with Gradient Methods ICML 2023
ModelDiff: A Framework for Comparing Learning Algorithms ICML 2023
Provably and Practically Efficient Neural Contextual Bandits ICML 2023
Neural networks trained with SGD learn distributions of increasing complexity ICML 2023
Feature learning in deep classifiers through Intermediate Neural Collapse ICML 2023
How much does Initialization Affect Generalization? ICML 2023
Spurious Valleys and Clustering Behavior of Neural Networks ICML 2023
Linear CNNs Discover the Statistical Structure of the Dataset Using Only the Most Dominant Frequencies ICML 2023
Certifying Ensembles: A General Certification Theory with S-Lipschitzness ICML 2023
Stochastic Gradient Descent-Induced Drift of Representation in a Two-Layer Neural Network ICML 2023
Diffusion Models are Minimax Optimal Distribution Estimators ICML 2023
Neural signature kernels as infinite-width-depth-limits of controlled ResNets ICML 2023
Optimal Sets and Solution Paths of ReLU Networks ICML 2023
On the Convergence of Gradient Flow on Multi-layer Linear Models ICML 2023
Neural Network Approximations of PDEs Beyond Linearity: A Representational Perspective ICML 2023
A Kernel-Based View of Language Model Fine-Tuning ICML 2023
Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models ICML 2023
Scalable Transformer for PDE Surrogate Modeling NIPS 2023
An Inductive Bias for Tabular Deep Learning NIPS 2023
Softmax Bottleneck Makes Language Models Unable to Represent Multi-mode Word Distributions ACL 2022
On the Effectiveness of Iterative Learning Control L4DC 2022
Size and depth of monotone neural networks: interpolation and approximation NIPS 2022
A PAC-Bayesian Generalization Bound for Equivariant Networks NIPS 2022