Results 1 to 10 of about 252 (217)
On surrogate loss functions and f-divergences
Annals of Statistics, 2009 The goal of binary classification is to estimate a discriminant function $γ$ from observations of covariate vectors and corresponding binary labels. We consider an elaboration of this problem in which the covariates are not available directly but are transformed by a dimensionality-reducing quantizer $Q$.
Michael Jordan +2 more
exaly +4 more sources
A New Information-Theoretical Distance Measure for Evaluating Community Detection Algorithms [PDF]
Journal of Universal Computer Science, 2019 Community detection is a research area from network science dealing with the investigation of complex networks such as social or biological networks, aiming to identify subgroups (communities) of entities (nodes) that are more closely related to each ...
Mariam Haroutunian +2 more
doaj +3 more sources
Entropy, 2020 We consider a sub-class of the f-divergences satisfying a stronger convexity property, which we refer to as strongly convex, or κ-convex divergences. We derive new and old relationships, based on convexity arguments, between popular f-divergences.
James Melbourne
doaj +1 more source
Joint range of f-divergences [PDF]
2010 IEEE International Symposium on Information Theory, 2010 We provide a general method for evaluation of the joint range of f-divergences for two different functions f. Via topological arguments we prove that the joint range for general distributions equals the convex hull of the joint range achieved by the distributions on a two-element set.
Peter Harremoës, Igor Vajda
openaire +2 more sources
On the Converse Jensen-Type Inequality for Generalized f-Divergences and Zipf–Mandelbrot Law
Mathematics, 2022 Motivated by some recent investigations about the sharpness of the Jensen inequality, this paper deals with the sharpness of the converse of the Jensen inequality.
Mirna Rodić
doaj +1 more source
Sharp Inequalities for $f$-Divergences [PDF]
IEEE Transactions on Information Theory, 2014 $f$-divergences are a general class of divergences between probability measures which include as special cases many commonly used divergences in probability, mathematical statistics and information theory such as Kullback-Leibler divergence, chi-squared divergence, squared Hellinger distance, total variation distance etc.
Adityanand Guntuboyina +2 more
openaire +2 more sources
A new refinement of Jensen’s inequality with applications in information theory
Open Mathematics, 2020 In this paper, we present a new refinement of Jensen’s inequality with applications in information theory. The refinement of Jensen’s inequality is obtained based on the general functional in the work of Popescu et al.
Xiao Lei, Lu Guoxiang
doaj +1 more source
F-Divergences and Cost Function Locality in Generative Modelling with Quantum Circuits
Entropy, 2021 Generative modelling is an important unsupervised task in machine learning. In this work, we study a hybrid quantum-classical approach to this task, based on the use of a quantum circuit born machine. In particular, we consider training a quantum circuit
Chiara Leadbeater +3 more
doaj +1 more source
IEEE Transactions on Information Theory, 2016 IEEE Trans. on Information Theory, vol. 62, no. 11, pp. 5973--6006, November 2016. This manuscript is identical to the journal paper, apart of some additional material which includes Sections III-C and IV-F, and three technical ...
Igal Sason, Sergio Verdú
openaire +3 more sources
Refinements of the integral Jensen’s inequality generated by finite or infinite permutations
Journal of Inequalities and Applications, 2021 There are a lot of papers dealing with applications of the so-called cyclic refinement of the discrete Jensen’s inequality. A significant generalization of the cyclic refinement, based on combinatorial considerations, has recently been discovered by the ...
László Horváth
doaj +1 more source