{"id":{"repo_id":"mcmaster","oai_identifier":"oai:macsphere.mcmaster.ca:11375/28364"},"canonical_url":"https://search.ndltd.org/etd/mcmaster/oai:macsphere.mcmaster.ca:11375/28364","repository":{"repo_id":"mcmaster","name":"McMaster University","base_url":"https://macsphere.mcmaster.ca/server/oai/request"},"display":{"title":"Polynomial time and private learning of unbounded Gaussian Mixture Models","abstract":"We develop a technique for privately estimating the parameters of a mixture distribution by reducing the problem to its non-private counterpart. This technique allows us to privatize existing non-private algorithms in a BlackBox manner while only incurring a small overhead in sample complexity and running time. As the main application of our framework, we develop an algorithm for privately learning mixtures of Gaussians using the non-private algorithm of Moitra and Valiant [MV10] as a BlackBox and incurs only a polynomial time overhead in the sample complexity and computational complexity. As a result, this gives the first sample complexity upper bound and the first polynomial time algorithm in d for learning the parameters of the Gaussian Mixture Models privately without requiring any boundedness assumptions on the parameters. To prove the results we introduced Private Populous Estimator (PPE) which is a generalized version of the one used in [AL22] to achieve (ϵ, δ)-differential privacy. We also develop a new masking mechanism for a single Gaussian component. Then we introduce a general recipe to turn a masking mechanism for a component into a masking mechanism for mixtures.","abstract_html":"We develop a technique for privately estimating the parameters of a mixture distribution by reducing the problem to its non-private counterpart. This technique allows us to privatize existing non-private algorithms in a BlackBox manner while only incurring a small overhead in sample complexity and running time. As the main application of our framework, we develop an algorithm for privately learning mixtures of Gaussians using the non-private algorithm of Moitra and Valiant [MV10] as a BlackBox and incurs only a polynomial time overhead in the sample complexity and computational complexity. As a result, this gives the first sample complexity upper bound and the first polynomial time algorithm in d for learning the parameters of the Gaussian Mixture Models privately without requiring any boundedness assumptions on the parameters. To prove the results we introduced Private Populous Estimator (PPE) which is a generalized version of the one used in [AL22] to achieve (ϵ, δ)-differential privacy. We also develop a new masking mechanism for a single Gaussian component. Then we introduce a general recipe to turn a masking mechanism for a component into a masking mechanism for mixtures.","abstract_has_math":false,"creators":["Arbas, Jamil"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Computer Science","school":null,"contributors":[],"advisors":["Ashtiani, Hassan"],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023","date_published":"2023","updated_at":"2026-11-18T19:37:13Z","subjects":["Differential Privacy","Gaussian Mixture Models"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://doi.org/10.71548/18106"],"render_values":[{"text":"https://doi.org/10.71548/18106","href":"https://doi.org/10.71548/18106","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/11375/28364","outbound_label":"Handle","outbound_source":"dc:identifier.uri","record_url":"http://hdl.handle.net/11375/28364","record_label":"Repository record","record_kind":"handle","record_source":"dc:identifier.uri","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://macsphere.mcmaster.ca/server/oai/request?verb=GetRecord&metadataPrefix=dim&identifier=oai%3Amacsphere.mcmaster.ca%3A11375%2F28364","prefix":"dim"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Ashtiani, Hassan"]},{"key":"dc:contributor.department","label":"Department","values":["Computer Science"]},{"key":"dc:creator","label":"Author","values":["Arbas, Jamil"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2023-03-17T20:02:21Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2023-03-17T20:02:21Z"]},{"key":"dc:date.issued","label":"Date","values":["2023"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Differential Privacy","Gaussian Mixture Models"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/11375/28364","https://doi.org/10.71548/18106"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["We develop a technique for privately estimating the parameters of a mixture distribution by reducing the problem to its non-private counterpart. This technique allows us to privatize existing non-private algorithms in a BlackBox manner while only incurring a small overhead in sample complexity and running time. As the main application of our framework, we develop an algorithm for privately learning mixtures of Gaussians using the non-private algorithm of Moitra and Valiant [MV10] as a BlackBox and incurs only a polynomial time overhead in the sample complexity and computational complexity. As a result, this gives the first sample complexity upper bound and the first polynomial time algorithm in d for learning the parameters of the Gaussian Mixture Models privately without requiring any boundedness assumptions on the parameters. To prove the results we introduced Private Populous Estimator (PPE) which is a generalized version of the one used in [AL22] to achieve (ϵ, δ)-differential privacy. We also develop a new masking mechanism for a single Gaussian component. Then we introduce a general recipe to turn a masking mechanism for a component into a masking mechanism for mixtures."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Master of Science (MSc)"]},{"key":"dc:title","label":"Title","values":["Polynomial time and private learning of unbounded Gaussian Mixture Models"]},{"key":"others:access_status","label":"Others Access Status","values":["open.access"]}]}],"canonical_facts":{"dc:contributor.advisor":["Ashtiani, Hassan"],"dc:contributor.department":["Computer Science"],"dc:creator":["Arbas, Jamil"],"dc:date.accessioned":["2023-03-17T20:02:21Z"],"dc:date.available":["2023-03-17T20:02:21Z"],"dc:date.issued":["2023"],"dc:description.abstract":["We develop a technique for privately estimating the parameters of a mixture distribution by reducing the problem to its non-private counterpart. This technique allows us to privatize existing non-private algorithms in a BlackBox manner while only incurring a small overhead in sample complexity and running time. As the main application of our framework, we develop an algorithm for privately learning mixtures of Gaussians using the non-private algorithm of Moitra and Valiant [MV10] as a BlackBox and incurs only a polynomial time overhead in the sample complexity and computational complexity. As a result, this gives the first sample complexity upper bound and the first polynomial time algorithm in d for learning the parameters of the Gaussian Mixture Models privately without requiring any boundedness assumptions on the parameters. To prove the results we introduced Private Populous Estimator (PPE) which is a generalized version of the one used in [AL22] to achieve (ϵ, δ)-differential privacy. We also develop a new masking mechanism for a single Gaussian component. Then we introduce a general recipe to turn a masking mechanism for a component into a masking mechanism for mixtures."],"dc:description.degree":["Master of Science (MSc)"],"dc:identifier.uri":["http://hdl.handle.net/11375/28364","https://doi.org/10.71548/18106"],"dc:language.iso":["en"],"dc:subject":["Differential Privacy","Gaussian Mixture Models"],"dc:title":["Polynomial time and private learning of unbounded Gaussian Mixture Models"],"dc:type":["Thesis"],"others:access_status":["open.access"]},"updated_at":"2026-11-18T19:37:13Z"}