English
Related papers

Related papers: Bounding the interleaving distance on concrete cat…

200 papers

Persistent homology analysis provides means to capture the connectivity structure of data sets in various dimensions. On the mathematical level, by defining a metric between the objects that persistence attaches to data sets, we can…

Machine Learning · Computer Science 2019-06-12 Henri Riihimäki , José Licón-Saláiz

Motivated both by theoretical and practical considerations in topological data analysis, we generalize the $p$-Wasserstein distance on barcodes to multiparameter persistence modules. For each $p\in [1,\infty]$, we in fact introduce two such…

Algebraic Topology · Mathematics 2021-11-12 Håvard Bakke Bjerkevik , Michael Lesnick

Balancing performance trade-off on long-tail (LT) data distributions remains a long-standing challenge. In this paper, we posit that this dilemma stems from a phenomenon called "tail performance degradation" (the model tends to severely…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Shenghan Chen , Yiming Liu , Yanzhen Wang , Yujia Wang , Xiankai Lu

We consider the setting of Reeb graphs of piecewise linear functions and study distances between them that are stable, meaning that functions which are similar in the supremum norm ought to have similar Reeb graphs. We define an edit…

Algebraic Topology · Mathematics 2021-02-09 Ulrich Bauer , Claudia Landi , Facundo Memoli

An important problem in the field of Topological Data Analysis is defining topological summaries which can be combined with traditional data analytic tools. In recent work Bubenik introduced the persistence landscape, a stable…

Algebraic Topology · Mathematics 2018-12-27 Oliver Vipond

Topological data analysis is becoming a popular way to study high dimensional feature spaces without any contextual clues or assumptions. This paper concerns itself with one popular topological feature, which is the number of…

Algebraic Topology · Mathematics 2016-05-31 Rushil Anirudh , Vinay Venkataraman , Karthikeyan Natesan Ramamurthy , Pavan Turaga

A number of machine learning algorithms are using a metric, or a distance, in order to compare individuals. The Euclidean distance is usually employed, but it may be more efficient to learn a parametric distance such as Mahalanobis metric.…

Machine Learning · Computer Science 2016-12-16 Hoel Le Capitaine

Multidimensional persistence has been proposed to study the persistence of topological features in data indexed by multiple parameters. In this work, we further explore its algebraic complications from the point of view of higher…

Representation Theory · Mathematics 2020-12-07 Mickaël Buchet , Emerson G. Escolar

Gait recognition is a unique biometric technique that can be performed at a long distance non-cooperatively and has broad applications in public safety and intelligent traffic systems. Previous gait works focus more on minimizing the…

Computer Vision and Pattern Recognition · Computer Science 2022-10-14 Weichen Yu , Hongyuan Yu , Yan Huang , Liang Wang

We address the problem of computing a textural loss based on the statistics extracted from the feature activations of a convolutional neural network optimized for object recognition (e.g. VGG-19). The underlying mathematical problem is the…

Computer Vision and Pattern Recognition · Computer Science 2021-03-12 Eric Heitz , Kenneth Vanhoey , Thomas Chambon , Laurent Belcour

Unsupervised embeddings are fundamental to numerous machine learning applications, yet their evaluation remains a challenging task. Traditional assessment methods often rely on extrinsic variables, such as performance in downstream tasks,…

Machine Learning · Computer Science 2024-08-01 Steven N. Hart , Thomas E. Tavolara

Permutation codes have recently garnered substantial research interest due to their potential in various applications including cloud storage systems, genome resequencing and flash memories. In this paper, we study the theoretical bounds…

Information Theory · Computer Science 2020-01-06 Siyi Yang , Clayton Schoeny , Lara Dolecek

Persistence diagrams are important descriptors in Topological Data Analysis. Due to the nonlinearity of the space of persistence diagrams equipped with their {\em diagram distances}, most of the recent attempts at using persistence diagrams…

Machine Learning · Computer Science 2019-08-09 Mathieu Carriere , Ulrich Bauer

The loss function is crucial to machine learning, especially in supervised learning frameworks. It is a fundamental component that controls the behavior and general efficacy of learning algorithms. However, despite their widespread use,…

Machine Learning · Computer Science 2026-02-09 Soumi Mahato , Lineesh M. C

We propose an algebraic setup for end-to-end physical-layer network coding based on submodule transmission. We introduce a distance function between modules, describe how it relates to information loss and errors, and show how to compute…

Information Theory · Computer Science 2016-11-15 Elisa Gorla , Alberto Ravagnani

The theory of persistence modules on the commutative ladders $CL_n(\tau)$ provides an extension of persistent homology. However, an efficient algorithm to compute the generalized persistence diagrams is still lacking. In this work, we view…

Representation Theory · Mathematics 2018-09-26 Hideto Asashiba , Emerson G. Escolar , Yasuaki Hiraoka , Hiroshi Takeuchi

Algorithms in machine learning and AI do critically depend on at least three key components: (i) the risk function, which is the expectation of the loss function, (ii) the function space, which is often called the hypothesis space, and…

Machine Learning · Statistics 2026-05-08 Lena Helgerth , Andreas Christmann

Persistence modules are representations of products of totally ordered sets in the category of vector spaces. They appear naturally in the representation theory of algebras, but in recent years they have also found applications in other…

Algebraic Topology · Mathematics 2024-11-04 Steve Oudot

Robust M-estimation uses loss functions, such as least absolute deviation (LAD), quantile loss and Huber's loss, to construct its objective function, in order to for example eschew the impact of outliers, whereas the difficulty in analysing…

Econometrics · Economics 2023-01-18 Chaohua Dong , Jiti Gao , Yundong Tu , Bin Peng

Metric learning is central to retrieval, yet its effects on embedding geometry and optimization dynamics are not well understood. We introduce a diagnostic framework, VARIANCE (intra-/inter-class variance) and GREEDINESS (active ratio and…

Computer Vision and Pattern Recognition · Computer Science 2026-01-30 Donghuo Zeng , Hao Niu , Zhi Li , Masato Taya