paper-with-me

홈 › Papers

Saddlepoints in Unsupervised Least Squares

2021-04-11 · Samuel Gerber

This paper sheds light on the risk landscape of unsupervised least squares in the context of deep auto-encoding neural nets. We formally establish an equivalence between unsupervised least squares and principal manifolds. This link provides insight into the risk landscape of auto--encoding under the mean squared error, in particular all non-trivial critical points are saddlepoints. Finding saddlepoints is in itself difficult, overcomplete auto-encoding poses the additional challenge that the saddlepoints are degenerate. Within this context we discuss regularization of auto-encoders, in particular bottleneck, denoising and contraction auto-encoding and propose a new optimization strategy that can be framed as particular form of contractive regularization.

📄 PDF Abstract BibTeX arXiv:2104.05000

Code (0)

등록된 구현이 없습니다.

Tasks

Denoising

Similar Papers 제목 키워드 기반

Deep least-squares methods: an unsupervised learning-based numerical method for solving elliptic PDEs

2019-11-05 · Zhiqiang Cai, Jingshuang Chen, Min Liu, Xinyu Liu

This paper studies an unsupervised deep learning-based numerical approach for solving partial differential equations (PDEs). The approach makes use of the deep neural network to approximate solutions of PDEs through the …

K-Means Kernel Classifier

2020-12-23 · M. Andrecut

We combine K-means clustering with the least-squares kernel classification method. K-means clustering is used to extract a set of representative vectors for each class. The least-squares kernel method uses these represen…

ClassificationClusteringGeneral Classification

Deep Least Squares Alignment for Unsupervised Domain Adaptation

2021-11-03 · Youshan Zhang, Brian D. Davison

Unsupervised domain adaptation leverages rich information from a labeled source domain to model an unlabeled target domain. Existing methods attempt to align the cross-domain distributions. However, the statistical repre…

Domain AdaptationUnsupervised Domain Adaptation

Whitening-Free Least-Squares Non-Gaussian Component Analysis

2016-03-03 · Hiroaki Shiino, Hiroaki Sasaki, Gang Niu, Masashi Sugiyama

Non-Gaussian component analysis (NGCA) is an unsupervised linear dimension reduction method that extracts low-dimensional non-Gaussian "signals" from high-dimensional data contaminated with Gaussian noise. NGCA can be re…

Dimensionality Reduction

Hybrid Least Squares/Gradient Descent Methods for DeepONets

2025-08-21 · Jun Choi, Chang-Ock Lee, Minam Moon arxiv

We propose an efficient hybrid least squares/gradient descent method to accelerate DeepONet training. Since the output of DeepONet can be viewed as linear with respect to the last layer parameters of the branch network, …