English
Related papers

Related papers: Isotropy, Clusters, and Classifiers

200 papers

Most generative models for clustering implicitly assume that the number of data points in each cluster grows linearly with the total number of data points. Finite mixture models, Dirichlet process mixture models, and Pitman--Yor process…

Methodology · Statistics 2015-12-03 Jeffrey Miller , Brenda Betancourt , Abbas Zaidi , Hanna Wallach , Rebecca C. Steorts

Centralized training is the standard paradigm in deep learning, enabling models to learn from a unified dataset in a single location. In such setup, isotropic feature distributions naturally arise as a mean to support well-structured and…

Machine Learning · Computer Science 2026-02-09 Chiara Lanza , Roberto Pereira , Marco Miozzo , Eduard Angelats , Paolo Dini

This paper considers metric spaces where distances between a pair of nodes are represented by distance intervals. The goal is to study methods for the determination of hierarchical clusters, i.e., a family of nested partitions indexed by a…

Social and Information Networks · Computer Science 2016-10-17 Weiyu Huang , Alejandro Ribeiro

Previous work has shown that the representations output by contextual language models are more anisotropic than static type embeddings, and typically display outlier dimensions. This seems to be true for both monolingual and multilingual…

Computation and Language · Computer Science 2023-06-08 Katharina Hämmerl , Alina Fastowski , Jindřich Libovický , Alexander Fraser

This paper introduces the equiwide clustering problem, where valid partitions must satisfy intra-cluster dissimilarity constraints. Unlike most existing clustering algorithms, equiwide clustering relies neither on density nor on a…

Machine Learning · Computer Science 2021-09-29 Jennie Andersen , Brice Chardin , Mohamed Tribak

In empirical work it is common to estimate parameters of models and report associated standard errors that account for "clustering" of units, where clusters are defined by factors such as geography. Clustering adjustments are typically…

Statistics Theory · Mathematics 2022-09-21 Alberto Abadie , Susan Athey , Guido Imbens , Jeffrey Wooldridge

In this short note we extend some of the recent results on matrix completion under the assumption that the columns of the matrix can be grouped (clustered) into subspaces (not necessarily disjoint or independent). This model deviates from…

Information Theory · Computer Science 2017-08-04 Vaneet Aggarwal , Shuchin Aeron

Scientists in many fields have the common and basic need of dimensionality reduction: visualizing the underlying structure of the massive multivariate data in a low-dimensional space. However, many dimensionality reduction methods confront…

Machine Learning · Statistics 2015-03-19 Teng Qiu , Yongjie Li

This paper serves a twofold purpose. First, a unified perspective on diversity indices is introduced based on an entropic basis. It is shown that the class of all linear combinations of the entropic basis, referred to as the class of linear…

Statistics Theory · Mathematics 2020-01-22 Zhiyi Zhang , Michael Grabchak

Clustering is an unsupervised technique of Data Mining. It means grouping similar objects together and separating the dissimilar ones. Each object in the data set is assigned a class label in the clustering process using a distance measure.…

Information Retrieval · Computer Science 2011-10-13 Parul Agarwal , M. Afshar Alam , Ranjit Biswas

Recent research in cross-lingual word embeddings has almost exclusively focused on offline methods, which independently train word embeddings in different languages and map them to a shared space through linear transformations. While…

Computation and Language · Computer Science 2021-12-28 Aitor Ormazabal , Mikel Artetxe , Gorka Labaka , Aitor Soroa , Eneko Agirre

While several feature embedding models have been developed in the literature, comparisons of these embeddings have largely focused on their numerical performance in classification-related downstream applications. However, an interpretable…

Machine Learning · Computer Science 2025-08-19 Mohammad Jalali , Bahar Dibaei Nia , Farzan Farnia

In the paper, it is given isomorphic classification of $F$-spaces of $log$-integrable measurable functions constructed using different measure spaces. At the same time, it is proved that such spaces are non-isometric.

Functional Analysis · Mathematics 2020-09-25 R. Z. Abdullaev , B. A. Madaminov

Nearly all practical neural models for classification are trained using cross-entropy loss. Yet this ubiquitous choice is supported by little theoretical or empirical evidence. Recent work (Hui & Belkin, 2020) suggests that training using…

Machine Learning · Computer Science 2023-02-09 Like Hui , Mikhail Belkin , Stephen Wright

We study quasi-isometric embeddings of symmetric spaces and non-uniform irreducible lattices in semisimple higher rank Lie groups. We show that any quasi-isometric embedding between symmetric spaces of the same rank can be decomposed into a…

Differential Geometry · Mathematics 2019-06-11 Thang Nguyen

Recent studies have revealed that neural networks learn interpretable algorithms for many simple problems. However, little is known about how these algorithms emerge during training. In this article, I study the training dynamics of a small…

Machine Learning · Computer Science 2024-10-29 Tiberiu Musat

Embedders play a central role in machine learning, projecting any object into numerical representations that can, in turn, be leveraged to perform various downstream tasks. The evaluation of embedding models typically depends on…

Machine Learning · Computer Science 2024-11-19 Maxime Darrin , Philippe Formont , Ismail Ben Ayed , Jackie CK Cheung , Pablo Piantanida

The ability to identify and control different kinds of linguistic information encoded in vector representations of words has many use cases, especially for explainability and bias removal. This is usually done via a set of simple…

Computation and Language · Computer Science 2023-10-25 Tal Levy , Omer Goldman , Reut Tsarfaty

We study supervised learning problems using clustering constraints to impose structure on either features or samples, seeking to help both prediction and interpretation. The problem of clustering features arises naturally in text…

Machine Learning · Computer Science 2016-09-20 Vincent Roulet , Fajwel Fogel , Alexandre d'Aspremont , Francis Bach

Existing algorithms for aligning cross-lingual word vector spaces assume that vector spaces are approximately isomorphic. As a result, they perform poorly or fail completely on non-isomorphic spaces. Such non-isomorphism has been…

Computation and Language · Computer Science 2020-10-21 Ivan Vulić , Sebastian Ruder , Anders Søgaard