The DOI matches its Crossref record; 77 of the 79 references it cites were found in a registry or an index.
On the Jensen–Shannon Symmetrization of Distances Relying on Abstract Means
Open accessAbstract
The Jensen–Shannon divergence is a renowned bounded symmetrization of the unbounded Kullback–Leibler divergence which measures the total Kullback–Leibler divergence to the average mixture distribution. However, the Jensen–Shannon divergence between Gaussian distributions is not available in closed form. To bypass this problem, we present a generalization of the Jensen–Shannon (JS) divergence using abstract means which yields closed-form expressions when the mean is chosen according to the parametric family of distributions. More generally, we define the JS-symmetrizations of any distance using parameter mixtures derived from abstract means. In particular, we first show that the geometric mean is well-suited for exponential families, and report two closed-form formula for (i) the geometric Jensen–Shannon divergence between probability densities of the same exponential family; and (ii) the geometric JS-symmetrization of the reverse Kullback–Leibler divergence between probability densities of the same exponential family. As a second illustrating example, we show that the harmonic mean is well-suited for the scale Cauchy distributions, and report a closed-form formula for the harmonic Jensen–Shannon divergence between scale Cauchy distributions. Applications to clustering with respect to these novel Jensen–Shannon divergences are touched upon.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The PoE and MoE can be subsumed under the concept of abstract means (Nielsen, 2019).”
From Generalized Multimodal ELBO (2021) · cites this paper as Nielsen, 2019
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“This insight has practical implications, because the choice of mean function directly influences the properties of a model (Nielsen, 2019).”
From Generalized Multimodal ELBO (2021) · cites this paper as Nielsen, 2019
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Labaca-Castro, R. (2023) · Springer eBooks · doi:10.1007/978-3-658-40442-0_9 · Cited by 21,119
McLachlan, G., & Peel, D. (2000) · Wiley Series in Probability and Statistics · doi:10.1002/0471721182 · Cited by 10,991
(2007) · doi:10.5555/1283383.1283494 · Cited by 7,364
Divergence measures based on the Shannon entropy
Lin, J.-H. (1991) · IEEE Transactions on Information Theory · doi:10.1109/18.61115 · Cited by 5,877
On Measures of Entropy and Information
Rényi, A. (1961) · Project Euclid (Cornell University) · Cited by 4,031
Hawkes, J., & Billingsley, P. (1987) · Journal of the Royal Statistical Society Series A (General) · doi:10.2307/2982048 · Cited by 1,765
The Minimum Description Length Principle
Grünwald, P. D. (2007) · doi:10.7551/mitpress/4643.001.0001 · Cited by 1,644
Clustering with Bregman Divergences
Banerjee, A., Merugu, S., Dhillon, I. S., & Ghosh, J. (2004) · SIAM International Conference on Data Mining · doi:10.1137/1.9781611972740.22 · Cited by 1,507
Information-type measures of difference of probability distributions and indirect observation
Csiszár, I. (1967) · Studia Scientiarum Mathematicarum Hungarica · Cited by 1,349
Information Geometry and Its Applications
Амари, Ш.-И. (2016) · Applied mathematical sciences · doi:10.1007/978-4-431-55978-8 · Cited by 1,166
Research works printed but not linked: 3
- Kafka, 1991, On powers of f-divergences defining a distance, Stud. Sci. Math. Hung., 26, 415
- Watanabe, 2004, Kullback information of normal mixture is not an analytic function, IEICE Tech. Rep. Neurocomput., 104, 41
- Tzagkarakis, G., and Tsakalides, P. (2004, January 21–23). A statistical approach to texture image retrieval via alpha-stable modeling of wavelet decompositions. Proceedings of the 5th International Workshop on Image Analysis for Multimedia Interactive Services, Instituto Superior Técnico, Lisboa, Portugal.
Cited by
Sorted by citations
RFLA: Gaussian Receptive Field Based Label Assignment for Tiny Object Detection
Xu, C., Wang, J., Yang, W. T., Yu, H., Yu, L., & Xia, G.-S. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20077-9_31 · Cited by 376
An Elementary Introduction to Information Geometry
Nielsen, F. (2020) · Entropy · doi:10.3390/e22101100 · Cited by 238
Self-citationOn a Generalization of the Jensen–Shannon Divergence and the Jensen–Shannon Centroid
Nielsen, F. (2020) · Entropy · doi:10.3390/e22020221 · Cited by 148
Self-citationDP-TrajGAN: A privacy-aware trajectory generation model with differential privacy
Zhang, J., Huang, Q., Huang, Y., Ding, Q., & Tsai, P. (2022) · Future Generation Computer Systems · doi:10.1016/j.future.2022.12.027 · Cited by 75
Generalized Jensen-Shannon Divergence Loss for Learning with Noisy LabelsPreprint
Englesson, E., & Azizpour, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.04522 · Cited by 69
Metadata
- Authors
- Nielsen, F.
- Affiliations
- Sony Computer Science Laboratories (JP)
- Corresponding author
- Nielsen, Frank
- ORCID
- Nielsen, Frank
- Venue
- Entropy
- Publisher
- MDPI AG
- Published
- 2019-05-11
- Volume
- 21
- Issue
- 5
- Pages
- 485
- ISSN
- 1099-4300 (ISSN-L)
- PMC
- PMC7514974
- OpenAlex
- W3102206498
- Cited by
- 257
- References
- 79
- Citations by year
- 2026: 38 · 2025: 63 · 2024: 40 · 2023: 42 · 2022: 27 · 2021: 30 · 2020: 12 · 2019: 5
- FWCI
- 8.56
- Type
- journal article
- Language
- en
- Open access
- gold
- dx.doi.org
- Licence
- Locations
- Entropy (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Physics and Astronomy › Statistical and Nonlinear Physics › Statistical Mechanics and Entropy
- Physical Sciences › Mathematics › Applied Mathematics › Mathematical Inequalities and Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Bayesian Methods and Mixture Models
- Keywords
- Jensen-Shannon divergence, geometric mean, harmonic mean, Kullback-Leibler divergence, exponential family, closed-form expressions, clustering
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
