← Optimization & Theory
Deep Learning › Optimization & Theory ›

Theory

1072 directly classified papers

Papers per year

Papers

The Implicit Regularization of Momentum Gradient Descent in Overparametrized Models AAAI 2023
Training Fully Connected Neural Networks is $\exists\mathbb{R}$-Complete NIPS 2023
On the Expressive Flexibility of Self-Attention Matrices AAAI 2023
Reversible and irreversible bracket-based dynamics for deep graph neural networks NIPS 2023
Critical Initialization of Wide and Deep Neural Networks using Partial Jacobians: General Theory and Applications NIPS 2023
What Makes Data Suitable for a Locally Connected Neural Network? A Necessary and Sufficient Condition Based on Quantum Entanglement. NIPS 2023
An Operator Theoretic Approach for Analyzing Sequence Neural Networks AAAI 2023
Learning Curves for Deep Structured Gaussian Feature Models NIPS 2023
An Inductive Bias for Tabular Deep Learning NIPS 2023
Training Neural Networks is NP-Hard in Fixed Dimension NIPS 2023
Benign Overfitting in Deep Neural Networks under Lazy Training ICML 2023
Analyzing and Diagnosing Pose Estimation With Attributions CVPR 2023
Experimental Observations of the Topology of Convolutional Neural Network Activations AAAI 2023
Nearly-tight Bounds for Deep Kernel Learning ICML 2023
Provable Dynamic Fusion for Low-Quality Multimodal Data ICML 2023
On Enhancing Expressive Power via Compositions of Single Fixed-Size ReLU Network ICML 2023
Effective Minkowski Dimension of Deep Nonparametric Regression: Function Approximation and Statistical Theories ICML 2023
Analyzing Convergence in Quantum Neural Networks: Deviations from Neural Tangent Kernels ICML 2023
Quantum Ridgelet Transform: Winning Lottery Ticket of Neural Networks with Quantum Computation ICML 2023
Finite-Sample Analysis of Learning High-Dimensional Single ReLU Neuron ICML 2023
On the Training Instability of Shuffling SGD with Batch Normalization ICML 2023
The Implicit Regularization of Dynamical Stability in Stochastic Gradient Descent ICML 2023
A Law of Robustness beyond Isoperimetry ICML 2023
Perturbation Analysis of Neural Collapse ICML 2023
Approximation and Estimation Ability of Transformers for Sequence-to-Sequence Functions with Infinite Dimensional Input ICML 2023