English
Related papers

Related papers: Geometry and Generalization: Eigenvalues as predic…

200 papers

High dimensional data is often assumed to be concentrated on or near a low-dimensional manifold. Autoencoders (AE) is a popular technique to learn representations of such data by pushing it through a neural network with a low dimension…

Machine Learning · Computer Science 2020-10-06 Amos Gropp , Matan Atzmon , Yaron Lipman

An additive autoencoder for dimension reduction, which is composed of a serially performed bias estimation, linear trend estimation, and nonlinear residual estimation, is proposed and analyzed. Computational experiments confirm that an…

Machine Learning · Computer Science 2022-10-14 Tommi Kärkkäinen , Jan Hänninen

Variational Autoencoders (VAEs) are well-established as a principled approach to probabilistic unsupervised learning with neural networks. Typically, an encoder network defines the parameters of a Gaussian distributed latent space from…

Machine Learning · Computer Science 2025-05-16 Alan Jeffares , Liyuan Liu

Deep neural networks are widely used for classification. These deep models often suffer from a lack of interpretability -- they are particularly difficult to understand because of their non-linear nature. As a result, neural networks are…

Artificial Intelligence · Computer Science 2017-11-22 Oscar Li , Hao Liu , Chaofan Chen , Cynthia Rudin

Variational auto-encoders (VAEs) have proven to be a well suited tool for performing dimensionality reduction by extracting latent variables lying in a potentially much smaller dimensional space than the data. Their ability to capture…

Machine Learning · Statistics 2020-10-23 Clément Chadebec , Clément Mantoux , Stéphanie Allassonnière

Autoencoders receive latent models of input data. It was shown in recent works that they also estimate probability density functions of the input. This fact makes using the Bayesian decision theory possible. If we obtain latent models of…

Computer Vision and Pattern Recognition · Computer Science 2018-11-07 Vasily Morzhakov

Deep neural network autoencoders are routinely used computationally for model reduction. They allow recognizing the intrinsic dimension of data that lie in a $k$-dimensional subset $K$ of an input Euclidean space $\mathbb{R}^n$. The…

Machine Learning · Computer Science 2024-02-20 Matthew D. Kvalheim , Eduardo D. Sontag

We analyze the distribution of eigenvectors for mesoscopic, mean-field perturbations of diagonal matrices in the bulk of the spectrum. Our results apply to a generalized $N\times N$ Rosenzweig-Porter model. We prove that the eigenvectors…

Probability · Mathematics 2020-11-04 Lucas Benigni

Generative adversarial networks (GANs) have emerged as a powerful unsupervised method to model the statistical patterns of real-world data sets, such as natural images. These networks are trained to map random inputs in their latent space…

Machine Learning · Computer Science 2021-03-19 Binxu Wang , Carlos R. Ponce

The recent theoretical analysis of deep neural networks in their infinite-width limits has deepened our understanding of initialisation, feature learning, and training of those networks, and brought new practical techniques for finding…

Machine Learning · Computer Science 2024-08-23 Taeyoung Kim , Hongseok Yang

We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold. Here, regularized autoencoders provide a popular approach by learning the identity mapping on the…

Computer Vision and Pattern Recognition · Computer Science 2024-05-14 Alexander Bauer , Shinichi Nakajima , Klaus-Robert Müller

We investigate random feature models in which neural networks sampled from a prescribed initialization ensemble are frozen and used as random features, with only the readout weights optimized. Adopting a statistical-physics viewpoint, we…

Machine Learning · Computer Science 2026-04-29 Taeyoung Kim

Deep generative models have made tremendous advances in image and signal representation learning and generation. These models employ the full Euclidean space or a bounded subset as the latent space, whose flat geometry, however, is often…

Machine Learning · Computer Science 2020-08-17 Stefan Schonsheck , Jie Chen , Rongjie Lai

The increasingly common applications of machine-learning schemes to atomic-scale simulations have triggered efforts to better understand the mathematical properties of the mapping between the Cartesian coordinates of the atoms and the…

Chemical Physics · Physics 2021-09-24 Sergey N. Pozdnyakov , Liwei Zhang , Christoph Ortner , Gábor Csányi , Michele Ceriotti

The variational auto-encoder (VAE) is a popular method for learning a generative model and embeddings of the data. Many real datasets are hierarchically structured. However, traditional VAEs map data in a Euclidean latent space which cannot…

Machine Learning · Statistics 2019-11-27 Emile Mathieu , Charline Le Lan , Chris J. Maddison , Ryota Tomioka , Yee Whye Teh

Graph self-supervised learning seeks to learn effective graph representations without relying on labeled data. Among various approaches, graph autoencoders (GAEs) have gained significant attention for their efficiency and scalability.…

Machine Learning · Computer Science 2025-06-17 Yang Liu , Deyu Bo , Wenxuan Cao , Yuan Fang , Yawen Li , Chuan Shi

Eigenvector perturbation analysis plays a vital role in various data science applications. A large body of prior works, however, focused on establishing $\ell_{2}$ eigenvector perturbation bounds, which are often highly inadequate in…

Statistics Theory · Mathematics 2022-07-06 Gen Li , Changxiao Cai , H. Vincent Poor , Yuxin Chen

Recently, deep generative models have become increasingly popular in unsupervised anomaly detection. However, deep generative models aim at recovering the data distribution rather than detecting anomalies. Besides, deep generative models…

Machine Learning · Computer Science 2019-11-15 Xuhong Wang , Ying Du , Shijie Lin , Ping Cui , Yuntian Shen , Yupu Yang

Subsurface imaging involves solving full waveform inversion (FWI) to predict geophysical properties from measurements. This problem can be reframed as an image-to-image translation, with the usual approach being to train an encoder-decoder…

Geophysics · Physics 2024-05-22 Yinan Feng , Yinpeng Chen , Peng Jin , Shihang Feng , Zicheng Liu , Youzuo Lin

This work introduces the concept of tangent space regularization for neural-network models of dynamical systems. The tangent space to the dynamics function of many physical systems of interest in control applications exhibits useful…

Machine Learning · Computer Science 2018-06-27 Fredrik Bagge Carlson , Rolf Johansson , Anders Robertsson