@inproceedings{gao_efficient_2015,
	title = {Efficient {Estimation} of {Mutual} {Information} for {Strongly} {Dependent} {Variables}},
	url = {https://proceedings.mlr.press/v38/gao15.html},
	abstract = {We demonstrate that a popular class of non-parametric mutual information (MI) estimators based on k-nearest-neighbor graphs requires number of samples that scales exponentially with the true MI. Consequently, accurate estimation of MI between two strongly dependent variables is possible only for prohibitively large sample size. This important yet overlooked shortcoming of the existing estimators is due to their implicit reliance on  local uniformity of the underlying joint distribution. We introduce a new  estimator that is robust to local non-uniformity, works well with limited data, and is able to capture relationship strengths over many orders of magnitude. We demonstrate the superior performance of the proposed estimator on both synthetic and real-world data.},
	language = {en},
	urldate = {2022-11-09},
	booktitle = {Proceedings of the {Eighteenth} {International} {Conference} on {Artificial} {Intelligence} and {Statistics}},
	publisher = {PMLR},
	author = {Gao, Shuyang and Steeg, Greg Ver and Galstyan, Aram},
	month = feb,
	year = {2015},
	note = {ISSN: 1938-7228},
	pages = {277--286},
	file = {Full Text PDF:/Users/soumikp/Zotero/storage/VNMT4H7U/Gao et al. - 2015 - Efficient Estimation of Mutual Information for Str.pdf:application/pdf},
}

{"_id":"BqqYgHcJDk2MmjSsH","bibbaseid":"gao-steeg-galstyan-efficientestimationofmutualinformationforstronglydependentvariables-2015","downloads":0,"creationDate":"2017-11-25T01:41:28.850Z","title":"Efficient Estimation of Mutual Information for Strongly Dependent Variables","author_short":["Gao, S.","Steeg, G. V.","Galstyan, A."],"year":2015,"bibtype":"inproceedings","biburl":"https://bibbase.org/f/Ceciz2iNjTZgQNtDc/mypubs_mar_2024.bib","bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Efficient Estimation of Mutual Information for Strongly Dependent Variables","url":"https://proceedings.mlr.press/v38/gao15.html","abstract":"We demonstrate that a popular class of non-parametric mutual information (MI) estimators based on k-nearest-neighbor graphs requires number of samples that scales exponentially with the true MI. Consequently, accurate estimation of MI between two strongly dependent variables is possible only for prohibitively large sample size. This important yet overlooked shortcoming of the existing estimators is due to their implicit reliance on local uniformity of the underlying joint distribution. We introduce a new estimator that is robust to local non-uniformity, works well with limited data, and is able to capture relationship strengths over many orders of magnitude. We demonstrate the superior performance of the proposed estimator on both synthetic and real-world data.","language":"en","urldate":"2022-11-09","booktitle":"Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics","publisher":"PMLR","author":[{"propositions":[],"lastnames":["Gao"],"firstnames":["Shuyang"],"suffixes":[]},{"propositions":[],"lastnames":["Steeg"],"firstnames":["Greg","Ver"],"suffixes":[]},{"propositions":[],"lastnames":["Galstyan"],"firstnames":["Aram"],"suffixes":[]}],"month":"February","year":"2015","note":"ISSN: 1938-7228","pages":"277–286","file":"Full Text PDF:/Users/soumikp/Zotero/storage/VNMT4H7U/Gao et al. - 2015 - Efficient Estimation of Mutual Information for Str.pdf:application/pdf","bibtex":"@inproceedings{gao_efficient_2015,\n\ttitle = {Efficient {Estimation} of {Mutual} {Information} for {Strongly} {Dependent} {Variables}},\n\turl = {https://proceedings.mlr.press/v38/gao15.html},\n\tabstract = {We demonstrate that a popular class of non-parametric mutual information (MI) estimators based on k-nearest-neighbor graphs requires number of samples that scales exponentially with the true MI. Consequently, accurate estimation of MI between two strongly dependent variables is possible only for prohibitively large sample size. This important yet overlooked shortcoming of the existing estimators is due to their implicit reliance on local uniformity of the underlying joint distribution. We introduce a new estimator that is robust to local non-uniformity, works well with limited data, and is able to capture relationship strengths over many orders of magnitude. We demonstrate the superior performance of the proposed estimator on both synthetic and real-world data.},\n\tlanguage = {en},\n\turldate = {2022-11-09},\n\tbooktitle = {Proceedings of the {Eighteenth} {International} {Conference} on {Artificial} {Intelligence} and {Statistics}},\n\tpublisher = {PMLR},\n\tauthor = {Gao, Shuyang and Steeg, Greg Ver and Galstyan, Aram},\n\tmonth = feb,\n\tyear = {2015},\n\tnote = {ISSN: 1938-7228},\n\tpages = {277--286},\n\tfile = {Full Text PDF:/Users/soumikp/Zotero/storage/VNMT4H7U/Gao et al. - 2015 - Efficient Estimation of Mutual Information for Str.pdf:application/pdf},\n}\n\n","author_short":["Gao, S.","Steeg, G. V.","Galstyan, A."],"key":"gao_efficient_2015","id":"gao_efficient_2015","bibbaseid":"gao-steeg-galstyan-efficientestimationofmutualinformationforstronglydependentvariables-2015","role":"author","urls":{"Paper":"https://proceedings.mlr.press/v38/gao15.html"},"metadata":{"authorlinks":{}},"html":""},"search_terms":["efficient","estimation","mutual","information","strongly","dependent","variables","gao","steeg","galstyan"],"keywords":[],"authorIDs":[],"dataSources":["dDcybAPCHBAZER5nc","AfBybHaxyt33K5MBP","m8Y57GfgnRrMKZTQS","epk5yKhDyD37NAsSC"]}