Derives layer-wise recursions for finite-width tensors under orthogonal initialization that reproduce the observed large-depth stability of nonlinear networks.
All you need is a good init
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
abstract
Layer-sequential unit-variance (LSUV) initialization - a simple method for weight initialization for deep net learning - is proposed. The method consists of the two steps. First, pre-initialize weights of each convolution or inner-product layer with orthonormal matrices. Second, proceed from the first to the final layer, normalizing the variance of the output of each layer to be equal to one. Experiment with different activation functions (maxout, ReLU-family, tanh) show that the proposed initialization leads to learning of very deep nets that (i) produces networks with test accuracy better or equal to standard methods and (ii) is at least as fast as the complex schemes proposed specifically for very deep nets such as FitNets (Romero et al. (2015)) and Highway (Srivastava et al. (2015)). Performance is evaluated on GoogLeNet, CaffeNet, FitNets and Residual nets and the state-of-the-art, or very close to it, is achieved on the MNIST, CIFAR-10/100 and ImageNet datasets.
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
A two-stage framework learns a world graph of pivotal states task-agnostically via joint training of a latent model and curiosity-driven policy, then uses the graph to accelerate hierarchical RL on maze tasks.
XPERT extracts and reuses cross-domain expert knowledge from pre-trained MoE LLMs via inference analysis and tensor decomposition to improve performance and convergence in downstream language model training.
A compact neural network surrogate maps weather features to grid voltages on a 6717-bus Texas system, enabling grid-aware weather forecasting that prioritizes operationally critical conditions like wind drops.
citing papers explorer
-
Criticality and Saturation in Orthogonal Neural Networks
Derives layer-wise recursions for finite-width tensors under orthogonal initialization that reproduce the observed large-depth stability of nonlinear networks.
-
Learning World Graphs to Accelerate Hierarchical Reinforcement Learning
A two-stage framework learns a world graph of pivotal states task-agnostically via joint training of a latent model and curiosity-driven policy, then uses the graph to accelerate hierarchical RL on maze tasks.
-
XPERT: Expert Knowledge Transfer for Effective Training of Language Models
XPERT extracts and reuses cross-domain expert knowledge from pre-trained MoE LLMs via inference analysis and tensor decomposition to improve performance and convergence in downstream language model training.
-
Learning the Weather-Grid Nexus via Weather-to-Voltage (W2V) Predictive Modeling
A compact neural network surrogate maps weather features to grid voltages on a 6717-bus Texas system, enabling grid-aware weather forecasting that prioritizes operationally critical conditions like wind drops.
- Margin-Adaptive Confidence Ranking for Reliable LLM Judgement
- Communication Dynamics Neural Networks: FFT-Diagonalized Layers for Improved Hessian Conditioning at Reduced Parameter Count