conftrace_

neural network initialization

33 papers

Explore in graph

Co-occurring keywords

neural network (6616) residual network (211) gradient descent (1144) network initialization (29) activation function (133) model compression (3302) free probability (4) convolutional neural network (4226) gaussian process (1200) neural network optimization (1293)

Papers

Tuning the Frequencies: Robust Training for Sinusoidal Neural Networks CVPR 2025
IniRetinex: Rethinking Retinex-type Low-Light Image Enhancer via Initialization Perspective AAAI 2025
VI^3NR: Variance Informed Initialization for Implicit Neural Representations CVPR 2025
From Activation to Initialization: Scaling Insights for Optimizing Neural Fields CVPR 2024
Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning NIPS 2024
Depth Degeneracy in Neural Networks: Vanishing Angles in Fully Connected ReLU Networks on Initialization JMLR 2024
Transformer as Linear Expansion of Learngene AAAI 2024
Lottery Tickets in Evolutionary Optimization: On Sparse Backpropagation-Free Trainability ICML 2023
Critical Initialization of Wide and Deep Neural Networks using Partial Jacobians: General Theory and Applications NIPS 2023
Are GATs Out of Balance? NIPS 2023
Randomness Is the Root of All Evil: More Reliable Evaluation of Deep Active Learning WACV 2023
The Neural Covariance SDE: Shaped Infinite Depth-and-Width Networks at Initialization NIPS 2022
A Flexible Meta Learning Model for Image Registration MIDL 2022
An Initial Alignment between Neural Network and Target is Needed for Gradient Descent to Learn ICML 2022
Partially-Random Initialization: A Smoking Gun for Binarization Hypothesis of BERT EMNLP 2022
Exact Solutions of a Deep Linear Network NIPS 2022
Free Probability for predicting the performance of feed-forward fully connected neural networks NIPS 2022
Towards Theoretically Inspired Neural Initialization Optimization NIPS 2022
Non-Gaussian Tensor Programs NIPS 2022
Multicoated Supermasks Enhance Hidden Networks ICML 2022
The future is log-Gaussian: ResNets and their infinite-depth-and-width limit at initialization NIPS 2021
Reducing Neural Network Parameter Initialization Into an SMT Problem (Student Abstract) AAAI 2021
GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training NIPS 2021
Doubly infinite residual neural networks: a diffusion process approach JMLR 2021
Beyond Signal Propagation: Is Feature Diversity Necessary in Deep Neural Network Initialization? ICML 2020