← Keywords

deep learning theory

36 papers

Explore in graph

Co-occurring keywords

neural tangent kernel (205) neural network (6616) relu network (143) neural network optimization (1293) deep learning (2111) deep network (152) network depth (29) representation learning (6174) gaussian process (1198) generalization bound (649)

Papers

REVISITING MULTI-PERMUTATION EQUIVARIANCE THROUGH THE LENS OF IRREDUCIBLE REPRESENTATIONS ICLR 2025
On the Hardness of Training Deep Neural Networks Discretely AAAI 2025
The Surprising Effectiveness of Infinite-Width NTKs for Characterizing and Improving Model Training AAAI 2025
Topological Generalization Bounds for Discrete-Time Stochastic Optimization Algorithms NIPS 2024
Graph Neural Networks Do Not Always Oversmooth NIPS 2024
Provable Tempered Overfitting of Minimal Nets and Typical Nets NIPS 2024
What Makes Data Suitable for a Locally Connected Neural Network? A Necessary and Sufficient Condition Based on Quantum Entanglement. NIPS 2023
Towards the Difficulty for a Deep Neural Network to Learn Concepts of Different Complexities NIPS 2023
Learning Curves for Deep Structured Gaussian Feature Models NIPS 2023
How Does Information Bottleneck Help Deep Learning? ICML 2023
Synergy and Symmetry in Deep Learning: Interactions between the Data, Model, and Inference Algorithm ICML 2022
Transition to Linearity of General Neural Networks with Directed Acyclic Graph Architecture NIPS 2022
Spectral Bias Outside the Training Set for Deep Networks in the Kernel Regime NIPS 2022
Universality of Group Convolutional Neural Networks Based on Ridgelet Analysis on Groups NIPS 2022
Deep Limits and a Cut-Off Phenomenon for Neural Networks JMLR 2022
Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent JMLR 2022
Neural Tangent Kernel Beyond the Infinite-Width Limit: Effects of Depth and Initialization ICML 2022
Reverse Engineering the Neural Tangent Kernel ICML 2022
Rank Diminishing in Deep Neural Networks NIPS 2022
Deep Frequency Principle Towards Understanding Why Deeper Learning Is Faster AAAI 2021
Implicit Regularization via Neural Feature Alignment AISTATS 2021
Align, then memorise: the dynamics of learning with feedback alignment ICML 2021
On the Random Conjugate Kernel and Neural Tangent Kernel ICML 2021
The Hintons in your Neural Network: a Quantum Field Theory View of Deep Learning ICML 2021
Why Do Deep Residual Networks Generalize Better than Deep Feedforward Networks? --- A Neural Tangent Kernel Perspective NIPS 2020