conftrace_

neural network theory

35 papers

Explore in graph

Co-occurring keywords

neural network (6616) neural network optimization (1293) gradient descent (1144) representation learning (6206) convolutional neural network (4226) feature learning (1311) activation function (133) relu network (143) theoretical analysis (97) learning theory (519)

Papers

Barriers to Discrete Reasoning with Transformers: A Survey Across Depth, Exactness, and Bandwidth EACL 2026
Mean-Field Analysis for Learning Subspace-Sparse Polynomials with Gaussian Input NIPS 2024
The effect of Leaky ReLUs on the training and generalization of overparameterized networks AISTATS 2024
Understanding Transformer Reasoning Capabilities via Graph Algorithms NIPS 2024
On Computational Limits of Modern Hopfield Models: A Fine-Grained Complexity Analysis ICML 2024
Learnability of high-dimensional targets by two-parameter models and gradient flow NIPS 2024
On the Power of Small-size Graph Neural Networks for Linear Programming NIPS 2024
Wide Two-Layer Networks can Learn from Adversarial Perturbations NIPS 2024
A provable control of sensitivity of neural networks through a direct parameterization of the overall bi-Lipschitzness NIPS 2024
On Bridging the Gap between Mean Field and Finite Width Deep Random Multilayer Perceptron with Batch Normalization ICML 2023
Multi-Layer Neural Networks as Trainable Ladders of Hilbert Spaces ICML 2023
Fundamental Limits of Two-layer Autoencoders, and Achieving Them with Gradient Methods ICML 2023
Complex-valued Neurons Can Learn More but Slower than Real-valued Neurons via Gradient Descent NIPS 2023
On Single-Index Models beyond Gaussian Data NIPS 2023
Width and Depth Limits Commute in Residual Networks ICML 2023
Gradient Descent in Neural Networks as Sequential Learning in Reproducing Kernel Banach Space ICML 2023
Towards the Difficulty for a Deep Neural Network to Learn Concepts of Different Complexities NIPS 2023
Transformers are uninterpretable with myopic methods: a case study with bounded Dyck grammars NIPS 2023
Understanding Multi-phase Optimization Dynamics and Rich Nonlinear Behaviors of ReLU Networks NIPS 2023
Theoretically Provable Spiking Neural Networks NIPS 2022
The Neural Covariance SDE: Shaped Infinite Depth-and-Width Networks at Initialization NIPS 2022
Benefits of Overparameterized Convolutional Residual Networks: Function Approximation under Smoothness Constraint ICML 2022
Universality of Group Convolutional Neural Networks Based on Ridgelet Analysis on Groups NIPS 2022
Local Identifiability of Deep ReLU Neural Networks: the Theory NIPS 2022
Thinking Like Transformers ICML 2021