English
Related papers

Related papers: Side Effects of Learning from Low-dimensional Data…

200 papers

We investigate the effect of the dimensionality of the representations learned in Deep Neural Networks (DNNs) on their robustness to input perturbations, both adversarial and random. To achieve low dimensionality of learned representations,…

Machine Learning · Computer Science 2020-02-20 Amartya Sanyal , Varun Kanade , Philip H. S. Torr , Puneet K. Dokania

Recent success in training deep neural networks have prompted active investigation into the features learned on their intermediate layers. Such research is difficult because it requires making sense of non-linear computations performed by…

Machine Learning · Computer Science 2016-03-01 Yixuan Li , Jason Yosinski , Jeff Clune , Hod Lipson , John Hopcroft

We explore the use of a topological manifold, represented as a collection of charts, as the target space of neural network based representation learning tasks. This is achieved by a simple adjustment to the output of an encoder's network…

Machine Learning · Computer Science 2021-06-15 Eric O. Korman

In this paper we present a mathematical framework on linking of embeddings of compact topological spaces into Euclidean spaces and separability of linked embeddings under a specific class of dimension reduction maps. As applications of the…

General Topology · Mathematics 2025-11-11 Xiao-Song Yang

We develop information geometric techniques to understand the representations learned by deep networks when they are trained on different tasks using supervised, meta-, semi-supervised and contrastive learning. We shed light on the…

Machine Learning · Computer Science 2023-07-25 Rahul Ramesh , Jialin Mao , Itay Griniasty , Rubing Yang , Han Kheng Teoh , Mark Transtrum , James P. Sethna , Pratik Chaudhari

Euclidean embeddings of data are fundamentally limited in their ability to capture latent semantic structures, which need not conform to Euclidean spatial assumptions. Here we consider an alternative, which embeds data as discrete…

Machine Learning · Computer Science 2019-05-10 Charlie Frogner , Farzaneh Mirzazadeh , Justin Solomon

Many techniques in machine learning attempt explicitly or implicitly to infer a low-dimensional manifold structure of an underlying physical phenomenon from measurements without an explicit model of the phenomenon or the measurement…

Machine Learning · Statistics 2023-07-04 Roy R. Lederman , Bogdan Toader

spectral-based subspace learning is a common data preprocessing step in many machine learning pipelines. The main aim is to learn a meaningful low dimensional embedding of the data. However, most subspace learning methods do not take into…

Machine Learning · Computer Science 2023-06-14 Firas Laakom , Jenni Raitoharju , Nikolaos Passalis , Alexandros Iosifidis , Moncef Gabbouj

Autoencoders, which consist of an encoder and a decoder, are widely used in machine learning for dimension reduction of high-dimensional data. The encoder embeds the input data manifold into a lower-dimensional latent space, while the…

Numerical Analysis · Mathematics 2024-03-29 Juliane Braunsmann , Marko Rajković , Martin Rumpf , Benedikt Wirth

The merit of projecting data onto linear subspaces is well known from, e.g., dimension reduction. One key aspect of subspace projections, the maximum preservation of variance (principal component analysis), has been thoroughly researched…

Machine Learning · Computer Science 2022-09-27 Erik Thordsen , Erich Schubert

Neural models learn representations of high-dimensional data on low-dimensional manifolds. Multiple factors, including stochasticities in the training process, model architectures, and additional inductive biases, may induce different…

Machine Learning · Computer Science 2025-12-02 Hanlin Yu , Berfin Inal , Georgios Arvanitidis , Soren Hauberg , Francesco Locatello , Marco Fumero

The manifold hypothesis posits that high-dimensional data typically resides on low-dimensional sub spaces. In this paper, we assume manifold hypothesis to investigate graph-based semi-supervised learning methods. In particular, we examine…

Machine Learning · Computer Science 2025-11-18 Mary Chriselda Antony Oliver , Michael Roberts , Carola-Bibiane Schönlieb , Matthew Thorpe

Learning in neural systems arises from synaptic changes that reshape the representations underlying behavior. While low-rank recurrent neural networks (RNNs) have emerged as a powerful framework for linking connectivity to function, a…

Machine Learning · Computer Science 2026-05-07 Yoav Ger , Omri Barak

The high-dimensional data setting, in which p >> n, is a challenging statistical paradigm that appears in many real-world problems. In this setting, learning a compact, low-dimensional representation of the data can substantially help…

Machine Learning · Computer Science 2018-08-07 Micol Marchetti-Bowick , Benjamin J. Lengerich , Ankur P. Parikh , Eric P. Xing

Network embedding is an effective technique to learn the low-dimensional representations of nodes in networks. Real-world networks are usually with multiplex or having multi-view representations from different relations. Recently, there has…

Machine Learning · Computer Science 2022-03-08 Qifan Wang , Yi Fang , Anirudh Ravula , Ruining He , Bin Shen , Jingang Wang , Xiaojun Quan , Dongfang Liu

Manifold learning (ML), known also as non-linear dimension reduction, is a set of methods to find the low dimensional structure of data. Dimension reduction for large, high dimensional data is not merely a way to reduce the data; the new…

Machine Learning · Statistics 2023-11-08 Marina Meilă , Hanyu Zhang

We investigate the geometric structure of learning dynamics in overparameterized transformer models through carefully controlled modular arithmetic tasks. Our primary finding is that despite operating in high-dimensional parameter spaces…

Machine Learning · Computer Science 2026-02-16 Yongzhong Xu

Modern deep neural networks are highly over-parameterized compared to the data on which they are trained, yet they often generalize remarkably well. A flurry of recent work has asked: why do deep networks not overfit to their training data?…

Machine Learning · Computer Science 2023-03-24 Minyoung Huh , Hossein Mobahi , Richard Zhang , Brian Cheung , Pulkit Agrawal , Phillip Isola

It is widely believed that natural image data exhibits low-dimensional structure despite the high dimensionality of conventional pixel representations. This idea underlies a common intuition for the remarkable success of deep learning in…

Computer Vision and Pattern Recognition · Computer Science 2021-04-20 Phillip Pope , Chen Zhu , Ahmed Abdelkader , Micah Goldblum , Tom Goldstein

Classification is a core topic in functional data analysis. A large number of functional classifiers have been proposed in the literature, most of which are based on functional principal component analysis or functional regression. In…

Methodology · Statistics 2025-10-14 Ruoxu Tan , Yiming Zang