English
Related papers

Related papers: Uniform Interpolation Constrained Geodesic Learnin…

200 papers

In this work, we propose to study the global geometrical properties of generative models. We introduce a new Riemannian metric to assess the similarity between any two data points. Importantly, our metric is agnostic to the parametrization…

Machine Learning · Computer Science 2024-07-17 Beomsu Kim , Michael Puthawala , Jong Chul Ye , Emanuele Sansone

We propose a new method for embedding graphs while preserving directed edge information. Learning such continuous-space vector representations (or embeddings) of nodes in a graph is an important first step for using network information…

Machine Learning · Computer Science 2017-09-15 Sami Abu-El-Haija , Bryan Perozzi , Rami Al-Rfou

The ability to represent and compare machine learning models is crucial in order to quantify subtle model changes, evaluate generative models, and gather insights on neural network architectures. Existing techniques for comparing data…

Unsupervised representation learning methods are widely used for gaining insight into high-dimensional, unstructured, or structured data. In some cases, users may have prior topological knowledge about the data, such as a known cluster…

Machine Learning · Computer Science 2023-11-08 Edith Heiter , Robin Vandaele , Tijl De Bie , Yvan Saeys , Jefrey Lijffijt

After training complex deep learning models, a common task is to compress the model to reduce compute and storage demands. When compressing, it is desirable to preserve the original model's per-example decisions (e.g., to go beyond top-1…

Machine Learning · Computer Science 2022-10-18 Jerry Chee , Megan Renz , Anil Damle , Christopher De Sa

A regularized version of Mixture Models is proposed to learn a principal graph from a distribution of $D$-dimensional data points. In the particular case of manifold learning for ridge detection, we assume that the underlying manifold can…

Machine Learning · Computer Science 2023-07-13 Tony Bonnaire , Aurélien Decelle , Nabila Aghanim

This work proposes an algorithm for explicitly constructing a pair of neural networks that linearize and reconstruct an embedded submanifold, from finite samples of this manifold. Our such-generated neural networks, called Flattening…

Machine Learning · Computer Science 2023-09-11 Michael Psenka , Druv Pai , Vishal Raman , Shankar Sastry , Yi Ma

Consider an i.i.d. sample from an unknown density function supported on an unknown manifold embedded in a high dimensional Euclidean space. We tackle the problem of learning a distance between points, able to capture both the geometry of…

Probability · Mathematics 2019-12-30 Pablo Groisman , Matthieu Jonckheere , Facundo Sapienza

This paper investigates the challenge of learning image manifolds, specifically pose manifolds, of 3D objects using limited training data. It proposes a DNN approach to manifold learning and for predicting images of objects for novel,…

Computer Vision and Pattern Recognition · Computer Science 2023-05-19 Shenyuan Liang , Pavan Turaga , Anuj Srivastava

Steering a language model - intervening on its internal activations to change downstream behaviour - has recently expanded beyond linear interpolation to nonlinear methods such as angular and kernelized steering, which define intervention…

Nonlinear manifolds are pervasive in deep visual features, where Euclidean distances can misrepresent true similarity. This mismatch is particularly detrimental to prototype-based interpretable fine-grained recognition, where even subtle…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Junhao Jia , Yunyou Liu , Yifei Sun , Huangwei Chen , Feiwei Qin , Changmiao Wang , Yong Peng

Mixup is a powerful data augmentation method that interpolates between two or more examples in the input or feature space and between the corresponding target labels. Many recent mixup methods focus on cutting and pasting two or more…

Computer Vision and Pattern Recognition · Computer Science 2022-03-29 Shashanka Venkataramanan , Ewa Kijak , Laurent Amsaleg , Yannis Avrithis

Interpolations in the latent space of deep generative models is one of the standard tools to synthesize semantically meaningful mixtures of generated samples. As the generator function is non-linear, commonly used linear interpolations in…

Machine Learning · Computer Science 2022-03-03 Henning Petzka , Ted Kronvall , Cristian Sminchisescu

An interpolation-based decoding scheme for interleaved subspace codes is presented. The scheme can be used as a (not necessarily polynomial-time) list decoder as well as a probabilistic unique decoder. Both interpretations allow to decode…

Information Theory · Computer Science 2014-08-07 Hannes Bartz , Antonia Wachter-Zeh

In image set classification, a considerable advance has been made by modeling the original image sets by second order statistics or linear subspace, which typically lie on the Riemannian manifold. Specifically, they are Symmetric Positive…

Computer Vision and Pattern Recognition · Computer Science 2018-05-31 Rui Wang , Xiao-Jun Wu , Kai-Xuan Chen , Josef Kittler

Manifold-learning techniques are routinely used in mining complex spatiotemporal data to extract useful, parsimonious data representations/parametrizations; these are, in turn, useful in nonlinear model identification tasks. We focus here…

Many statistical and machine learning approaches rely on pairwise distances between data points. The choice of distance metric has a fundamental impact on performance of these procedures, raising questions about how to appropriately…

Statistics Theory · Mathematics 2020-04-20 Didong Li , David B Dunson

Sparsity-based representations have recently led to notable results in various visual recognition tasks. In a separate line of research, Riemannian manifolds have been shown useful for dealing with features and models that do not lie in…

Machine Learning · Computer Science 2015-05-21 Mehrtash Harandi , Richard Hartley , Chunhua Shen , Brian Lovell , Conrad Sanderson

We propose a simple interpolation-based method for the efficient approximation of gradients in neural ODE models. We compare it with the reverse dynamic method (known in the literature as "adjoint method") to train neural ODEs on…

Neural and Evolutionary Computing · Computer Science 2020-11-03 Talgat Daulbaev , Alexandr Katrutsa , Larisa Markeeva , Julia Gusak , Andrzej Cichocki , Ivan Oseledets

Graph transformers typically embed every node in a single Euclidean space, blurring heterogeneous topologies. We prepend a lightweight Riemannian mixture-of-experts layer that routes each node to various kinds of manifold, mixture of…

Machine Learning · Computer Science 2025-07-11 Ankit Jyothish , Ali Jannesari
‹ Prev 1 8 9 10 Next ›