Results 21 to 30 of about 248 (141)
Comptes Rendus. Mécanique, 2023 With view on the context of convex thermomechanics, we propose tools based on the concept of Bregman divergence, a notion introduced in the 1960s and used in learning and optimization as well. This study is motivated by the need of “discrepancy measures”
Andrieux, Stéphane
doaj +1 more source
Hyperlink regression via Bregman divergence [PDF]
Neural Networks, 2020 41 pages, 14 ...
Akifumi Okuno, Hidetoshi Shimodaira
openaire +3 more sources
Beta-Divergence as a Subclass of Bregman Divergence [PDF]
IEEE Signal Processing Letters, 2011 In this paper, we present a complete proof that the β-divergence is a particular case of Bregman divergence. This little-known result makes it possible to straightforwardly apply theorems about Bregman divergences to β-divergences. This is of interest for numerous applications since these divergences are widely used, for instance in non-negative matrix
Romain Hennequin +2 more
openaire +1 more source
Convergence Rates of Gradient Methods for Convex Optimization in the Space of Measures
Open Journal of Mathematical Optimization, 2023 We study the convergence rate of Bregman gradient methods for convex optimization in the space of measures on a $d$-dimensional manifold. Under basic regularity assumptions, we show that the suboptimality gap at iteration $k$ is in $O(\log (k)k^{-1 ...
Chizat, Lénaïc
doaj +1 more source
The Bregman Chord Divergence [PDF]
, 2019 Distances are fundamental primitives whose choice significantly impacts the performances of algorithms in machine learning and signal processing. However selecting the most appropriate distance for a given task is an endeavor. Instead of testing one by one the entries of an ever-expanding dictionary of {\em ad hoc} distances, one rather prefers to ...
Frank Nielsen, Richard Nock
openaire +2 more sources
Algorithms, 2022 The family of α-divergences including the oriented forward and reverse Kullback–Leibler divergences is often used in signal processing, pattern recognition, and machine learning, among others.
Frank Nielsen
doaj +1 more source
Learning to Approximate a Bregman Divergence
CoRR, 2019 19 pages, 4 ...
Ali Siahkamari +4 more
openaire +4 more sources
Worst-case and smoothed analysis of k-means clustering with Bregman divergences
Journal of Computational Geometry, 2013 The k-means method is the method of choice for clustering large-scale data sets and it performs exceedingly well in practice despite its exponential worst-case running-time.
Bodo Manthey, Heiko Roeglin
doaj +1 more source
Log-Determinant Divergences Revisited: Alpha-Beta and Gamma Log-Det Divergences
Entropy, 2015 This work reviews and extends a family of log-determinant (log-det) divergences for symmetric positive definite (SPD) matrices and discusses their fundamental properties.
Andrzej Cichocki +2 more
doaj +1 more source
Neural Bregman Divergences for Distance Learning
CoRR, 2022 Many metric learning tasks, such as triplet learning, nearest neighbor retrieval, and visualization, are treated primarily as embedding tasks where the ultimate metric is some variant of the Euclidean distance (e.g., cosine or Mahalanobis), and the algorithm must learn to embed points into the pre-chosen space.
Fred Lu, Edward Raff, Francis Ferraro
openaire +3 more sources