paper-with-me

홈 › Papers

Eigenvalues of Autoencoders in Training and at Initialization

2022-01-27 · Benjamin Dees, Susama Agarwala, Corey Lowman

In this paper, we investigate the evolution of autoencoders near their initialization. In particular, we study the distribution of the eigenvalues of the Jacobian matrices of autoencoders early in the training process, training on the MNIST data set. We find that autoencoders that have not been trained have eigenvalue distributions that are qualitatively different from those which have been trained for a long time ($>$100 epochs). Additionally, we find that even at early epochs, these eigenvalue distributions rapidly become qualitatively similar to those of the fully trained autoencoders. We also compare the eigenvalues at initialization to pertinent theoretical work on the eigenvalues of random matrices and the products of such matrices.

📄 PDF Abstract BibTeX arXiv:2201.11813

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Autocorrelation Matters: Understanding the Role of Initialization Schemes for State Space Models

2024-11-29 · Fusheng Liu, Qianxiao Li

Current methods for initializing state space model (SSM) parameters primarily rely on the HiPPO framework \citep{gu2023how}, which is based on online function approximation with the SSM kernel basis. However, the HiPPO f…

State Space Models

IKUN: Initialization to Keep snn training and generalization great with sUrrogate-stable variaNce

2024-11-27 · Da Chang, DeLiang Wang, Xiao Yang

Weight initialization significantly impacts the convergence and performance of neural networks. While traditional methods like Xavier and Kaiming initialization are widely used, they often fall short for spiking neural n…

The Goldilocks zone: Towards better understanding of neural network loss landscapes

2018-07-06 · Stanislav Fort, Adam Scherlis

We explore the loss landscape of fully-connected and convolutional neural networks using random, low-dimensional hyperplanes and hyperspheres. Evaluating the Hessian, $H$, of the loss function on these hypersurfaces, we …

Implicit Greedy Rank Learning in Autoencoders via Overparameterized Linear Networks

2021-07-02 · Shih-Yu Sun, Vimal Thilak, Etai Littwin, Omid Saremi 외

Deep linear networks trained with gradient descent yield low rank solutions, as is typically studied in matrix factorization. In this paper, we take a step further and analyze implicit rank regularization in autoencoders…

Sensitivity

On compression rate of quantum autoencoders: Control design, numerical and experimental realization

2020-05-22 · Hailan Ma, Chang-Jiang Huang, Chunlin Chen, Daoyi Dong 외

Quantum autoencoders which aim at compressing quantum information in a low-dimensional latent space lie in the heart of automatic data compression in the field of quantum information. In this paper, we establish an upper…

Data Compression