Evolution of Eigenvalue Decay in Deep Networks
The linear transformations in converged deep networks show fast eigenvalue decay. The distribution of eigenvalues looks like a Heavy-tail distribution, where the vast majority of eigenvalues is small, but not actually zero, and only a few spikes of large eigenvalues exist. We use a stochastic approximator to generate histograms of eigenvalues. This allows us to investigate layers with hundreds of thousands of dimensions. We show how the distributions change over the course of image net training, converging to a similar heavy-tail spectrum across all intermediate layers.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Eigenvalue Decay Implies Polynomial-Time Learnability for Neural Networks
We consider the problem of learning function classes computed by neural networks with various activations (e.g. ReLU or Sigmoid), a task believed to be computationally intractable in the worst-case. A major open problem …
Modeling Nonlinear Dynamics in Continuous Time with Inductive Biases on Decay Rates and/or Frequencies
We propose a neural network-based model for nonlinear dynamics in continuous time that can impose inductive biases on decay rates and/or frequencies. Inductive biases are helpful for training neural networks especially w…
Time SeriesTime Series AnalysisOn the Benefits of Active Data Collection in Operator Learning
We investigate active data collection strategies for operator learning when the target operator is linear and the input functions are drawn from a mean-zero stochastic process with continuous covariance kernels. With an …
Operator learningDeep Learning with Eigenvalue Decay Regularizer
This paper extends our previous work on regularization of neural networks using Eigenvalue Decay by employing a soft approximation of the dominant eigenvalue in order to enable the calculation of its derivatives in relat…
ClassificationDeep LearningGeneral Classificationimage-classification+3Nearly Optimal Algorithms with Sublinear Computational Complexity for Online Kernel Regression
The trade-off between regret and computational cost is a fundamental problem for online kernel regression, and previous algorithms worked on the trade-off can not keep optimal regret bounds at a sublinear computational c…
regression