{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/108187"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/108187","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Co-generation with GANs using AIS based HMC","abstract":"Inferring the most likely configuration for a subset of variables of a joint distribution given the remaining ones – which we refer to as co-generation – is an important challenge that is computationally demanding for all but the simplest settings. This task has received a considerable amount of attention, particularly for classical ways of modeling distributions like structured prediction. In contrast, almost nothing is known about this task when considering recently proposed techniques for modeling high-dimensional distributions, particularly generative adversarial nets (GANs). Therefore, in this paper, we study the occurring challenges for co-generation with GANs. To address those challenges we develop an annealed importance sampling based Hamiltonian Monte Carlo co-generation algorithm. The presented approach significantly outperforms classical gradient based methods on a synthetic and on the CelebA and LSUN datasets.","abstract_html":"Inferring the most likely configuration for a subset of variables of a joint distribution given the remaining ones – which we refer to as co-generation – is an important challenge that is computationally demanding for all but the simplest settings. This task has received a considerable amount of attention, particularly for classical ways of modeling distributions like structured prediction. In contrast, almost nothing is known about this task when considering recently proposed techniques for modeling high-dimensional distributions, particularly generative adversarial nets (GANs). Therefore, in this paper, we study the occurring challenges for co-generation with GANs. To address those challenges we develop an annealed importance sampling based Hamiltonian Monte Carlo co-generation algorithm. The presented approach significantly outperforms classical gradient based methods on a synthetic and on the CelebA and LSUN datasets.","abstract_has_math":false,"creators":["Fang, Tiantian"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Schwing, Alexander"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-08-26T23:58:48Z","date_published":"2020-08-26T23:58:48Z","updated_at":"2026-07-22T22:24:47Z","subjects":["Co-Generation, generative model, annealed importance sampling"],"languages":["en"],"rights":["Copyright 2020 Tiantian Fang"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/108187","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Schwing, Alexander"]},{"key":"dc:creator","label":"Author","values":["Fang, Tiantian"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2020-08-26T23:58:48Z","2022-08-26T23:58:55Z","2020-05-14","2020-05"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Co-Generation, generative model, annealed importance sampling"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2020 Tiantian Fang"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/108187"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Inferring the most likely configuration for a subset of variables of a joint distribution given the remaining ones – which we refer to as co-generation – is an important challenge that is computationally demanding for all but the simplest settings. This task has received a considerable amount of attention, particularly for classical ways of modeling distributions like structured prediction. In contrast, almost nothing is known about this task when considering recently proposed techniques for modeling high-dimensional distributions, particularly generative adversarial nets (GANs). Therefore, in this paper, we study the occurring challenges for co-generation with GANs. To address those challenges we develop an annealed importance sampling based Hamiltonian Monte Carlo co-generation algorithm. The presented approach significantly outperforms classical gradient based methods on a synthetic and on the CelebA and LSUN datasets.","Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2022-05-01","The student, Tiantian Fang, accepted the attached license on 2020-05-12 at 12:19.","The student, Tiantian Fang, submitted this Thesis for approval on 2020-05-12 at 12:32.","This Thesis was approved for publication on 2020-05-14 at 08:30.","DSpace SAF Submission Ingestion Package generated from Vireo submission #15350 on 2020-08-25 at 17:31:03","Made available in DSpace on 2020-08-26T23:58:48Z (GMT). No. of bitstreams: 2 FANG-THESIS-2020.pdf: 45750283 bytes, checksum: 1346ac6e629304508cbdb347fde15c9f (MD5) LICENSE.txt: 4210 bytes, checksum: 317a732460c22f9c8a22be7533b29968 (MD5) Previous issue date: 2020-05-14","Embargo set by: Seth Robbins for item 115800 Lift date: 2022-08-26T23:58:55Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","U of I Only"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Co-generation with GANs using AIS based HMC"]}]}],"canonical_facts":{"dc:contributor":["Schwing, Alexander"],"dc:creator":["Fang, Tiantian"],"dc:date":["2020-08-26T23:58:48Z","2022-08-26T23:58:55Z","2020-05-14","2020-05"],"dc:description":["Inferring the most likely configuration for a subset of variables of a joint distribution given the remaining ones – which we refer to as co-generation – is an important challenge that is computationally demanding for all but the simplest settings. This task has received a considerable amount of attention, particularly for classical ways of modeling distributions like structured prediction. In contrast, almost nothing is known about this task when considering recently proposed techniques for modeling high-dimensional distributions, particularly generative adversarial nets (GANs). Therefore, in this paper, we study the occurring challenges for co-generation with GANs. To address those challenges we develop an annealed importance sampling based Hamiltonian Monte Carlo co-generation algorithm. The presented approach significantly outperforms classical gradient based methods on a synthetic and on the CelebA and LSUN datasets.","Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2022-05-01","The student, Tiantian Fang, accepted the attached license on 2020-05-12 at 12:19.","The student, Tiantian Fang, submitted this Thesis for approval on 2020-05-12 at 12:32.","This Thesis was approved for publication on 2020-05-14 at 08:30.","DSpace SAF Submission Ingestion Package generated from Vireo submission #15350 on 2020-08-25 at 17:31:03","Made available in DSpace on 2020-08-26T23:58:48Z (GMT). No. of bitstreams: 2 FANG-THESIS-2020.pdf: 45750283 bytes, checksum: 1346ac6e629304508cbdb347fde15c9f (MD5) LICENSE.txt: 4210 bytes, checksum: 317a732460c22f9c8a22be7533b29968 (MD5) Previous issue date: 2020-05-14","Embargo set by: Seth Robbins for item 115800 Lift date: 2022-08-26T23:58:55Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","U of I Only"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/108187"],"dc:language":["en"],"dc:rights":["Copyright 2020 Tiantian Fang"],"dc:subject":["Co-Generation, generative model, annealed importance sampling"],"dc:title":["Co-generation with GANs using AIS based HMC"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:47Z"}