[{"doi":"10.48550/arXiv.1804.11130","oa":1,"main_file_link":[{"url":"https://doi.org/10.48550/arXiv.1804.11130","open_access":"1"}],"date_updated":"2024-10-14T12:31:09Z","department":[{"_id":"FrLo"}],"language":[{"iso":"eng"}],"date_created":"2023-09-13T12:20:49Z","author":[{"last_name":"Locatello","first_name":"Francesco","id":"26cfd52f-2483-11ee-8040-88983bcc06d4","full_name":"Locatello, Francesco","orcid":"0000-0002-4850-0683"},{"last_name":"Vincent","full_name":"Vincent, Damien","first_name":"Damien"},{"last_name":"Tolstikhin","first_name":"Ilya","full_name":"Tolstikhin, Ilya"},{"full_name":"Rätsch, Gunnar","first_name":"Gunnar","last_name":"Rätsch"},{"first_name":"Sylvain","full_name":"Gelly, Sylvain","last_name":"Gelly"},{"last_name":"Schölkopf","full_name":"Schölkopf, Bernhard","first_name":"Bernhard"}],"year":"2018","date_published":"2018-04-30T00:00:00Z","external_id":{"arxiv":["1804.11130"]},"publication_status":"submitted","article_processing_charge":"No","oa_version":"Preprint","title":"Competitive training of mixtures of independent deep generative models","month":"04","day":"30","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","publication":"arXiv","extern":"1","article_number":"1804.11130","arxiv":1,"citation":{"ama":"Locatello F, Vincent D, Tolstikhin I, Rätsch G, Gelly S, Schölkopf B. Competitive training of mixtures of independent deep generative models. <i>arXiv</i>. doi:<a href=\"https://doi.org/10.48550/arXiv.1804.11130\">10.48550/arXiv.1804.11130</a>","apa":"Locatello, F., Vincent, D., Tolstikhin, I., Rätsch, G., Gelly, S., &#38; Schölkopf, B. (n.d.). Competitive training of mixtures of independent deep generative models. <i>arXiv</i>. <a href=\"https://doi.org/10.48550/arXiv.1804.11130\">https://doi.org/10.48550/arXiv.1804.11130</a>","ista":"Locatello F, Vincent D, Tolstikhin I, Rätsch G, Gelly S, Schölkopf B. Competitive training of mixtures of independent deep generative models. arXiv, 1804.11130.","mla":"Locatello, Francesco, et al. “Competitive Training of Mixtures of Independent Deep Generative Models.” <i>ArXiv</i>, 1804.11130, doi:<a href=\"https://doi.org/10.48550/arXiv.1804.11130\">10.48550/arXiv.1804.11130</a>.","ieee":"F. Locatello, D. Vincent, I. Tolstikhin, G. Rätsch, S. Gelly, and B. Schölkopf, “Competitive training of mixtures of independent deep generative models,” <i>arXiv</i>. .","chicago":"Locatello, Francesco, Damien Vincent, Ilya Tolstikhin, Gunnar Rätsch, Sylvain Gelly, and Bernhard Schölkopf. “Competitive Training of Mixtures of Independent Deep Generative Models.” <i>ArXiv</i>, n.d. <a href=\"https://doi.org/10.48550/arXiv.1804.11130\">https://doi.org/10.48550/arXiv.1804.11130</a>.","short":"F. Locatello, D. Vincent, I. Tolstikhin, G. Rätsch, S. Gelly, B. Schölkopf, ArXiv (n.d.)."},"_id":"14327","status":"public","fulldoi":"https://doi.org/10.48550/arXiv.1804.11130","type":"preprint","abstract":[{"lang":"eng","text":"A common assumption in causal modeling posits that the data is generated by a\r\nset of independent mechanisms, and algorithms should aim to recover this\r\nstructure. Standard unsupervised learning, however, is often concerned with\r\ntraining a single model to capture the overall distribution or aspects thereof.\r\nInspired by clustering approaches, we consider mixtures of implicit generative\r\nmodels that ``disentangle'' the independent generative mechanisms underlying\r\nthe data. Relying on an additional set of discriminators, we propose a\r\ncompetitive training procedure in which the models only need to capture the\r\nportion of the data distribution from which they can produce realistic samples.\r\nAs a by-product, each model is simpler and faster to train. We empirically show\r\nthat our approach splits the training distribution in a sensible way and\r\nincreases the quality of the generated samples."}]},{"user_id":"c635000d-4b10-11ee-a964-aac5a93f6ac1","day":"21","publication":"Proceedings of the 20th International Conference on Artificial Intelligence and Statistics","citation":{"ama":"Locatello F, Khanna R, Tschannen M, Jaggi M. A unified optimization view on generalized matching pursuit and Frank-Wolfe. In: <i>Proceedings of the 20th International Conference on Artificial Intelligence and Statistics</i>. Vol 54. ML Research Press; 2017:860-868.","ista":"Locatello F, Khanna R, Tschannen M, Jaggi M. 2017. A unified optimization view on generalized matching pursuit and Frank-Wolfe. Proceedings of the 20th International Conference on Artificial Intelligence and Statistics. AISTATS: Conference on Artificial Intelligence and Statistics vol. 54, 860–868.","apa":"Locatello, F., Khanna, R., Tschannen, M., &#38; Jaggi, M. (2017). A unified optimization view on generalized matching pursuit and Frank-Wolfe. In <i>Proceedings of the 20th International Conference on Artificial Intelligence and Statistics</i> (Vol. 54, pp. 860–868). Fort Lauderdale, FL, United States: ML Research Press.","mla":"Locatello, Francesco, et al. “A Unified Optimization View on Generalized Matching Pursuit and Frank-Wolfe.” <i>Proceedings of the 20th International Conference on Artificial Intelligence and Statistics</i>, vol. 54, ML Research Press, 2017, pp. 860–68.","ieee":"F. Locatello, R. Khanna, M. Tschannen, and M. Jaggi, “A unified optimization view on generalized matching pursuit and Frank-Wolfe,” in <i>Proceedings of the 20th International Conference on Artificial Intelligence and Statistics</i>, Fort Lauderdale, FL, United States, 2017, vol. 54, pp. 860–868.","chicago":"Locatello, Francesco, Rajiv Khanna, Michael Tschannen, and Martin Jaggi. “A Unified Optimization View on Generalized Matching Pursuit and Frank-Wolfe.” In <i>Proceedings of the 20th International Conference on Artificial Intelligence and Statistics</i>, 54:860–68. ML Research Press, 2017.","short":"F. Locatello, R. Khanna, M. Tschannen, M. Jaggi, in:, Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, ML Research Press, 2017, pp. 860–868."},"_id":"14205","status":"public","quality_controlled":"1","oa":1,"language":[{"iso":"eng"}],"year":"2017","date_published":"2017-02-21T00:00:00Z","article_processing_charge":"No","oa_version":"Preprint","title":"A unified optimization view on generalized matching pursuit and Frank-Wolfe","month":"02","extern":"1","arxiv":1,"type":"conference","abstract":[{"lang":"eng","text":"Two of the most fundamental prototypes of greedy optimization are the matching pursuit and Frank-Wolfe algorithms. In this paper, we take a unified view on both classes of methods, leading to the first explicit convergence rates of matching pursuit methods in an optimization sense, for general sets of atoms. We derive sublinear (1/t) convergence for both classes on general smooth objectives, and linear convergence on strongly convex objectives, as well as a clear correspondence of algorithm variants. Our presented algorithms and rates are affine invariant, and do not need any incoherence or sparsity assumptions."}],"volume":54,"main_file_link":[{"url":"https://doi.org/10.48550/arXiv.1702.06457","open_access":"1"}],"publisher":"ML Research Press","page":"860-868","date_updated":"2023-09-13T09:49:10Z","intvolume":"        54","department":[{"_id":"FrLo"}],"date_created":"2023-08-22T14:17:19Z","author":[{"orcid":"0000-0002-4850-0683","full_name":"Locatello, Francesco","first_name":"Francesco","id":"26cfd52f-2483-11ee-8040-88983bcc06d4","last_name":"Locatello"},{"first_name":"Rajiv","full_name":"Khanna, Rajiv","last_name":"Khanna"},{"full_name":"Tschannen, Michael","first_name":"Michael","last_name":"Tschannen"},{"first_name":"Martin","full_name":"Jaggi, Martin","last_name":"Jaggi"}],"conference":{"name":"AISTATS: Conference on Artificial Intelligence and Statistics","start_date":"2017-04-20","end_date":"2017-04-22","location":"Fort Lauderdale, FL, United States"},"external_id":{"arxiv":["1702.06457"]},"publication_status":"published"},{"article_processing_charge":"No","oa_version":"Preprint","publication_status":"published","conference":{"start_date":"2017-12-04","end_date":"2017-12-09","location":"Long Beach, CA, United States","name":"NeurIPS: Neural Information Processing Systems"},"external_id":{"arxiv":["1705.11041"]},"department":[{"_id":"FrLo"}],"language":[{"iso":"eng"}],"date_updated":"2024-10-14T12:29:50Z","year":"2017","date_published":"2017-05-31T00:00:00Z","author":[{"last_name":"Locatello","orcid":"0000-0002-4850-0683","full_name":"Locatello, Francesco","first_name":"Francesco","id":"26cfd52f-2483-11ee-8040-88983bcc06d4"},{"full_name":"Tschannen, Michael","first_name":"Michael","last_name":"Tschannen"},{"last_name":"Rätsch","full_name":"Rätsch, Gunnar","first_name":"Gunnar"},{"first_name":"Martin","full_name":"Jaggi, Martin","last_name":"Jaggi"}],"date_created":"2023-08-22T14:17:38Z","main_file_link":[{"url":"https://arxiv.org/abs/1705.11041","open_access":"1"}],"oa":1,"type":"conference","abstract":[{"lang":"eng","text":"Greedy optimization methods such as Matching Pursuit (MP) and Frank-Wolfe (FW) algorithms regained popularity in recent years due to their simplicity, effectiveness and theoretical guarantees. MP and FW address optimization over the linear span and the convex hull of a set of atoms, respectively. In this paper, we consider the intermediate case of optimization over the convex cone, parametrized as the conic hull of a generic atom set, leading to the first principled definitions of non-negative MP algorithms for which we give explicit convergence rates and demonstrate excellent empirical performance. In particular, we derive sublinear (O(1/t)) convergence on general smooth and convex objectives, and linear convergence (O(e−t)) on strongly convex objectives, in both cases for general sets of atoms. Furthermore, we establish a clear correspondence of our algorithms to known algorithms from the MP and FW literature. Our novel algorithms and analyses target general atom sets and general objective functions, and hence are directly applicable to a large variety of learning settings."}],"status":"public","quality_controlled":"1","citation":{"mla":"Locatello, Francesco, et al. “Greedy Algorithms for Cone Constrained Optimization with Convergence Guarantees.” <i>Advances in Neural Information Processing Systems</i>, 2017.","ista":"Locatello F, Tschannen M, Rätsch G, Jaggi M. 2017. Greedy algorithms for cone constrained optimization with convergence guarantees. Advances in Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems.","apa":"Locatello, F., Tschannen, M., Rätsch, G., &#38; Jaggi, M. (2017). Greedy algorithms for cone constrained optimization with convergence guarantees. In <i>Advances in Neural Information Processing Systems</i>. Long Beach, CA, United States.","ama":"Locatello F, Tschannen M, Rätsch G, Jaggi M. Greedy algorithms for cone constrained optimization with convergence guarantees. In: <i>Advances in Neural Information Processing Systems</i>. ; 2017.","short":"F. Locatello, M. Tschannen, G. Rätsch, M. Jaggi, in:, Advances in Neural Information Processing Systems, 2017.","chicago":"Locatello, Francesco, Michael Tschannen, Gunnar Rätsch, and Martin Jaggi. “Greedy Algorithms for Cone Constrained Optimization with Convergence Guarantees.” In <i>Advances in Neural Information Processing Systems</i>, 2017.","ieee":"F. Locatello, M. Tschannen, G. Rätsch, and M. Jaggi, “Greedy algorithms for cone constrained optimization with convergence guarantees,” in <i>Advances in Neural Information Processing Systems</i>, Long Beach, CA, United States, 2017."},"_id":"14206","arxiv":1,"publication_identifier":{"isbn":["9781510860964"]},"extern":"1","title":"Greedy algorithms for cone constrained optimization with convergence guarantees","publication":"Advances in Neural Information Processing Systems","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","day":"31","month":"05"}]