neural network initialization

IniRetinex: Rethinking Retinex-type Low-Light Image Enhancer via Initialization Perspective AAAI 2025 Tuning the Frequencies: Robust Training for Sinusoidal Neural Networks CVPR 2025 VI^3NR: Variance Informed Initialization for Implicit Neural Representations CVPR 2025 Beyond IID weights: sparse and low-rank deep Neural Networks are also Gaussian Processes ICLR 2024 Depth Degeneracy in Neural Networks: Vanishing Angles in Fully Connected ReLU Networks on Initialization JMLR 2024 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 NeurIPS 2024 How connectivity structure shapes rich and lazy learning in neural circuits ICLR 2024 Transformer as Linear Expansion of Learngene AAAI 2024 Are GATs Out of Balance? NeurIPS 2023 Critical Initialization of Wide and Deep Neural Networks using Partial Jacobians: General Theory and Applications NeurIPS 2023 Lottery Tickets in Evolutionary Optimization: On Sparse Backpropagation-Free Trainability ICML 2023 Randomness Is the Root of All Evil: More Reliable Evaluation of Deep Active Learning WACV 2023 Symmetries, Flat Minima, and the Conserved Quantities of Gradient Flow ICLR 2023 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 Exact Solutions of a Deep Linear Network NeurIPS 2022 Free Probability for predicting the performance of feed-forward fully connected neural networks NeurIPS 2022 Multicoated Supermasks Enhance Hidden Networks ICML 2022 Non-Gaussian Tensor Programs NeurIPS 2022 Partially-Random Initialization: A Smoking Gun for Binarization Hypothesis of BERT EMNLP 2022 Proving the Lottery Ticket Hypothesis for Convolutional Neural Networks ICLR 2022 The Neural Covariance SDE: Shaped Infinite Depth-and-Width Networks at Initialization NeurIPS 2022 Towards Theoretically Inspired Neural Initialization Optimization NeurIPS 2022 Doubly infinite residual neural networks: a diffusion process approach JMLR 2021