The DOI matches its Crossref record.
Gaussian Partial Information Decomposition: Bias Correction and Application to High-dimensional Data
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?
In the citing paper
“Fourth, and unlike what was assumed in a previous study,30 the bias is highly uneven across PID components.”
From Sampling bias corrections for discrete and Gaussian partial information decompositions (2026) · cites this paper as [30]
In the citing paper
“While the problem of null models for information-theoretic quantities is gaining recognition,29 to our knowledge only two studies have investigated PID sampling bias, specifically for a Gaussian PID30 and for a PID with a mix of discrete and Gaussian variables.31”
From Sampling bias corrections for discrete and Gaussian partial information decompositions (2026) · cites this paper as [30]
In the citing paper
“It satisfies many desirable properties including additivity of all PID components for independent systems of sources and targets (proven for discrete33,46 and empirically validated for Gaussian PID30) and has been widely applied to neural data.13,36,37,47,48”
From Sampling bias corrections for discrete and Gaussian partial information decompositions (2026) · cites this paper as [30]
In the citing paper
“α = 1 corresponds to choosing parameter values exactly equal to those reported in Venkatesh et al.30 α > 1 reduces the total mutual information.”
From Sampling bias corrections for discrete and Gaussian partial information decompositions (2026) · cites this paper as Venkatesh et al. [30]
In the citing paper
“Although neither the discrete BROJA PID33 nor its Gaussian counterpart gPID30 have been defined for more than two sources as yet”
From Sampling bias corrections for discrete and Gaussian partial information decompositions (2026) · cites this paper as [30]
In the citing paper
“All our Gaussian bias corrections improve considerably the existing Venkatesh correction.30”
From Sampling bias corrections for discrete and Gaussian partial information decompositions (2026) · cites this paper as [30]
In the citing paper
“Applying this procedure to the discrete PID would have been not possible because it assumes an analytical knowledge of the bias, which is only available for the Gaussian case.”
From Sampling bias corrections for discrete and Gaussian partial information decompositions (2026) · cites this paper as Venkatesh et al. [30]
In the citing paper
“The Venkatesh correction assumes that the union information has the same proportional bias as the joint information (and thus of the synergy, see methods), and it then rescales all PID accordingly (Equations 3, 4, and 5).”
From Sampling bias corrections for discrete and Gaussian partial information decompositions (2026) · cites this paper as [30]
In the citing paper
“it empowers experimenters with bias-correction methods that greatly improve PID estimates with respect to uncorrected measures or other available methods.”
From Sampling bias corrections for discrete and Gaussian partial information decompositions (2026) · cites this paper as [30]
In the citing paper
“In the Gaussian case, analytical considerations (see Note S6) indicate that the union information bias depends only on the dimensionality of the covariance matrices d and on the number of trials N and not on the magnitude of the union information itself (as implicitly assumed in Equation 17 of Venkatesh et al.30).”
From Sampling bias corrections for discrete and Gaussian partial information decompositions (2026) · cites this paper as Venkatesh et al. [30]
In the citing paper
“Because the Venkatesh procedure relies on these incorrect proportional-bias assumptions, it misassigns the bias among PID components, especially when all PID terms are non-zero and the true union information does not match any of the Shannon information quantities (so that the rectification steps in Equations 106 and 107 of Venkatesh et al.30 do not correct the error).”
From Sampling bias corrections for discrete and Gaussian partial information decompositions (2026) · cites this paper as Venkatesh et al. [30]
In the citing paper
“then making the assumptions that the union information has the same proportional bias as the joint information, thus rescaling the bias of the union information accordingly (Equation 17 of Venkatesh et al.30).”
From Sampling bias corrections for discrete and Gaussian partial information decompositions (2026) · cites this paper as Venkatesh et al. [30]
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
No references could be resolved yet.
Research works printed but not linked: 34
- Saskia EJ de Vries, Jerome A Lecoq, Michael A Buice, Peter A Groblewski, Gabriel K Ocker, Michael Oliver, David Feng, Nicholas Cain, Peter Ledochowitsch, Daniel Millman, et al. A large-scale standardized physiological survey reveals functional organization of the mouse visual cortex. Nature neuroscience, 23 (1):138-151, 2020.
- Joshua H Siegle, Xiaoxuan Jia, Séverine Durand, Sam Gale, Corbett Bennett, Nile Graddis, Greggory Heller, Tamina K Ramirez, Hannah Choi, Jennifer A Luviano, et al. Survey of spiking in the mouse visual system reveals functional hierarchy. Nature, 592(7852):86-92, 2021.
- Elad Schneidman, William Bialek, and Michael J Berry. Synergy, redundancy, and independence in population codes. Journal of Neuroscience, 23(37):11539-11553, 2003.
- Itay Gat and Naftali Tishby. Synergy and redundancy among brain cells of behaving monkeys. Advances in neural information processing systems, 11, 1998.
- Giuseppe Pica, Eugenio Piasini, Houman Safaai, Caroline Runyan, Christopher Harvey, Mathew Diamond, Christoph Kayser, Tommaso Fellin, and Stefano Panzeri. Quantifying how much sensory information in a neural code is relevant for behavior. Advances in Neural Information Processing Systems, 30, 2017.
- Jan Bím, Vito De Feo, Daniel Chicharro, Malte Bieler, Ileana L Hanganu-Opatz, Andrea Brovelli, and Stefano Panzeri. A non-negative measure of feature-related information transfer between neural signals. BioRxiv, page 758128, 2019.
- Tomas Scagliarini, Luca Faes, Daniele Marinazzo, Sebastiano Stramaglia, and Rosario N Mantegna. Synergistic information transfer in the global system of financial markets. Entropy, 22(9):1000, 2020.
- Patricia Wollstadt, Sebastian Schmitt, and Michael Wibral. A rigorous information-theoretic definition of redundancy and relevancy in feature selection based on (partial) information decomposition. arXiv preprint arXiv:2105.04187, 2021. · arXiv
- Sanghamitra Dutta, Praveen Venkatesh, Piotr Mardziel, Anupam Datta, and Pulkit Grover. An information- theoretic quantification of discrimination with exempt features. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 3825-3833, 2020.
- Praveen Venkatesh and Gabriel Schamberg. Partial information decomposition via deficiency for multivari- ate gaussians. In 2022 IEEE International Symposium on Information Theory (ISIT), pages 2892-2897. IEEE, 2022.
- Adam B Barrett. Exploration of synergistic and redundant information sharing in static and dynamical Gaussian systems. Physical Review E, 91(5):052802, 2015.
- Jana Krohova, Luca Faes, Barbora Czippelova, Zuzana Turianikova, Nikoleta Mazgutova, Riccardo Pernice, Alessandro Busacca, Daniele Marinazzo, Sebastiano Stramaglia, and Michal Javorka. Multiscale informa- tion decomposition dissects control mechanisms of heart rate variability at rest and during physiological stress. Entropy, 21(5):526, 2019.
- Ari Pakman, Amin Nejatbakhsh, Dar Gilboa, Abdullah Makkeh, Luca Mazzucato, Michael Wibral, and Elad Schneidman. Estimating the unique information of continuous variables. Advances in neural information processing systems, 34:20295-20307, 2021.
- Nils Bertschinger, Johannes Rauh, Eckehard Olbrich, Jürgen Jost, and Nihat Ay. Quantifying unique information. Entropy, 16(4):2161-2183, 2014.
- Johannes Rauh, Pradeep Kr Banerjee, Eckehard Olbrich, Guido Montúfar, and Jürgen Jost. Continuity and additivity properties of information decompositions. arXiv preprint arXiv:2204.10982, 2022. · arXiv
- Pradeep Kr Banerjee, Johannes Rauh, and Guido Montúfar. Computing the unique information. In 2018 IEEE International Symposium on Information Theory (ISIT), pages 141-145. IEEE, 2018.
- Paul Pu Liang, Yun Cheng, Xiang Fan, Chun Kai Ling, Suzanne Nie, Richard Chen, Zihao Deng, Faisal Mahmood, Ruslan Salakhutdinov, and Louis-Philippe Morency. Quantifying & modeling feature interactions: An information decomposition framework. arXiv preprint arXiv:2302.12247, 2023. · arXiv
- Paul L Williams and Randall D Beer. Nonnegative decomposition of multivariate information. arXiv preprint arXiv:1004.2515, 2010. · arXiv
- Thomas M Cover and Joy A Thomas. Elements of Information Theory. John Wiley & Sons, 2012.
- Virgil Griffith and Christof Koch. Quantifying synergistic mutual information. In Guided self-organization: inception, pages 159-190. Springer, 2014.
- Malte Harder, Christoph Salge, and Daniel Polani. Bivariate measure of redundant information. Physical Review E, 87(1):012130, 2013.
- Artemy Kolchinsky. A novel approach to multivariate redundancy and synergy. arXiv preprint arXiv:1908.08642, 2019. · arXiv
- Joseph T Lizier, Nils Bertschinger, Jürgen Jost, and Michael Wibral. Information decomposition of target effects from multi-source interactions: perspectives on previous, current and future work. Entropy, 20(4): 307, 2018.
- Praveen Venkatesh, Keerthana Gurushankar, and Gabriel Schamberg. Capturing and interpreting unique information. arXiv preprint arXiv:2302.11873, 2023. · arXiv
- Pradeep Kr Banerjee, Eckehard Olbrich, Jürgen Jost, and Johannes Rauh. Unique informations and deficiencies. In 2018 56th Annual Allerton Conference on Communication, Control, and Computing (Allerton), pages 32-38. IEEE, 2018.
- Naftali Tishby, Fernando C Pereira, and William Bialek. The information bottleneck method. arXiv preprint physics/0004057, 2000. · arXiv
- Gal Chechik, Amir Globerson, Naftali Tishby, and Yair Weiss. Information bottleneck for gaussian variables. Advances in Neural Information Processing Systems, 16, 2003.
- Liam Paninski. Estimation of entropy and mutual information. Neural computation, 15(6):1191-1253, 2003.
- T Tony Cai, Tengyuan Liang, and Harrison H Zhou. Law of log determinant of sample covariance matrix and optimal estimation of differential entropy for high-dimensional gaussian distributions. Journal of Multivariate Analysis, 137:161-172, 2015.
- Larry Wasserman. All of statistics: a concise course in statistical inference, volume 26. Springer, 2004.
- Nicholas M Timme and Christopher Lapish. A tutorial for information theory in neuroscience. eneuro, 5 (3), 2018.
- Thomas M Cover and Joy A Thomas. Elements of Information Theory. John Wiley & Sons, 2012.
- F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825-2830, 2011.
- Joshua H Siegle, Xiaoxuan Jia, Séverine Durand, Sam Gale, Corbett Bennett, Nile Graddis, Greggory Heller, Tamina K Ramirez, Hannah Choi, Jennifer A Luviano, et al. Survey of spiking in the mouse visual system reveals functional hierarchy. Nature, 592(7852):86-92, 2021.
Cited by
Sorted by citations
Sampling bias corrections for discrete and Gaussian partial information decompositions
Lorenz, G. M., Engel, N. M., Koçillari, L., Celotto, M., Orsenigo, D., Curreli, S., Malerba, S. B., Engel, A. K., Kayser, C., Fellin, T., et al. (2026) · Patterns · doi:10.1016/j.patter.2026.101619 · Cited by 9
Metadata
- Authors
- Venkatesh, P., Bennett, C., Gale, S., Ramirez, T., Heller, G., Durand, S., Olsen, S., & Mihalas, S.
- Venue
- Advances in Neural Information Processing Systems 36
- Published
- 2023
- Pages
- 74602-74635
- Cited by
- 4
- References
- 0
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
