English
Related papers

Related papers: Loss Landscapes of Regularized Linear Autoencoders

200 papers

Real-world geometry and 3D vision tasks are replete with challenging symmetries that defy tractable analytical expression. In this paper, we introduce Neural Isometries, an autoencoder framework which learns to map the observation space to…

Computer Vision and Pattern Recognition · Computer Science 2024-10-31 Thomas W. Mitchel , Michael Taylor , Vincent Sitzmann

We develop data-driven methods for incorporating physical information for priors to learn parsimonious representations of nonlinear systems arising from parameterized PDEs and mechanics. Our approach is based on Variational Autoencoders…

Machine Learning · Computer Science 2021-03-17 Ryan Lopez , Paul J. Atzberger

This paper proposes a theoretical framework on the mechanism of autoencoders. To the encoder part, under the main use of dimensionality reduction, we investigate its two fundamental properties: bijective maps and data disentangling. The…

Machine Learning · Computer Science 2022-12-13 Changcun Huang

Measuring the similarity between data points often requires domain knowledge, which can in parts be compensated by relying on unsupervised methods such as latent-variable models, where similarity/distance is estimated in a more compact…

Machine Learning · Statistics 2020-08-13 Nutan Chen , Alexej Klushyn , Francesco Ferroni , Justin Bayer , Patrick van der Smagt

The joint optimization of the reconstruction and classification error is a hard non convex problem, especially when a non linear mapping is utilized. In order to overcome this obstacle, a novel optimization strategy is proposed, in which a…

Machine Learning · Computer Science 2022-11-07 Ioannis A. Nellas , Sotiris K. Tasoulis , Vassilis P. Plagianakos , Spiros V. Georgakopoulos

Autoencoders are frequently used for anomaly detection, both in the unsupervised and semi-supervised settings. They rely on the assumption that when trained using the reconstruction loss, they will be able to reconstruct normal data more…

Machine Learning · Computer Science 2025-01-24 Roel Bouman , Tom Heskes

Masked Autoencoders (MAEs) achieve impressive performance in image classification tasks, yet the internal representations they learn remain less understood. This work started as an attempt to understand the strong downstream classification…

Machine Learning · Computer Science 2026-02-04 Anika Shrivastava , Renu Rameshan , Samar Agnihotri

The Distributional Principal Autoencoder (DPA) combines distributionally correct reconstruction with principal-component-like interpretability of the encodings. In this work, we provide exact theoretical guarantees on both fronts. First, we…

Machine Learning · Statistics 2026-05-14 Andrej Leban

We explore the use of deep neural networks for nonlinear dimensionality reduction in climate applications. We train convolutional autoencoders (CAEs) to encode two temperature field datasets from pre-industrial control runs in the CMIP5…

Atmospheric and Oceanic Physics · Physics 2018-09-06 J. A. Saenz , N. Lubbers , N. M. Urban

Lane detection is crucial for vehicle localization which makes it the foundation for automated driving and many intelligent and advanced driving assistant systems. Available vision-based lane detection methods do not make full use of the…

Computer Vision and Pattern Recognition · Computer Science 2023-08-14 Ruohan Li , Yongqi Dong

Masked AutoEncoder (MAE) has revolutionized the field of self-supervised learning with its simple yet effective masking and reconstruction strategies. However, despite achieving state-of-the-art performance across various downstream vision…

Computer Vision and Pattern Recognition · Computer Science 2023-12-11 Xiaoyu Yue , Lei Bai , Meng Wei , Jiangmiao Pang , Xihui Liu , Luping Zhou , Wanli Ouyang

Visualization is a crucial step in exploratory data analysis. One possible approach is to train an autoencoder with low-dimensional latent space. Large network depth and width can help unfolding the data. However, such expressive networks…

Machine Learning · Computer Science 2023-07-03 Philipp Nazari , Sebastian Damrich , Fred A. Hamprecht

Modeling and controlling complex spatiotemporal dynamical systems driven by partial differential equations (PDEs) often necessitate dimensionality reduction techniques to construct lower-order models for computational efficiency. This paper…

Systems and Control · Electrical Eng. & Systems 2024-09-12 Priyabrata Saha , Saibal Mukhopadhyay

Sparse autoencoders have become a standard tool for uncovering interpretable latent representations in neural networks. Yet salient concepts often span manifolds that current linear methods cannot capture without post hoc analysis. This…

Machine Learning · Computer Science 2026-05-12 Thomas Dooms , Ward Gauderis , Geraint Wiggins , Jose Oramas

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

We study the problem of self-supervised structured representation learning using autoencoders for downstream tasks such as generative modeling. Unlike most methods which rely on matching an arbitrary, relatively unstructured, prior…

Machine Learning · Computer Science 2024-02-16 Felix Leeb , Guilia Lanzillotta , Yashas Annadani , Michel Besserve , Stefan Bauer , Bernhard Schölkopf

Sparse autoencoders (SAEs) are widely used to extract interpretable features from neural network representations, often under the implicit assumption that concepts correspond to independent linear directions. However, a growing body of…

Increasingly many real world tasks involve data in multiple modalities or views. This has motivated the development of many effective algorithms for learning a common latent space to relate multiple domains. However, most existing…

Computer Vision and Pattern Recognition · Computer Science 2017-11-17 Tanmoy Mukherjee , Makoto Yamada , Timothy M. Hospedales

Data-driven reduced-order models based on autoencoders generally lack interpretability compared to classical methods such as the proper orthogonal decomposition. More interpretability can be gained by disentangling the latent variables and…

Machine Learning · Computer Science 2025-02-21 Henning Schwarz , Pyei Phyo Lin , Jens-Peter M. Zemke , Thomas Rung

We develop data-driven methods incorporating geometric and topological information to learn parsimonious representations of nonlinear dynamics from observations. The approaches learn nonlinear state-space models of the dynamics for general…

Machine Learning · Computer Science 2025-03-28 Ryan Lopez , Paul J. Atzberger
‹ Prev 1 3 4 5 6 7 10 Next ›