Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Levy, K. Y."'
Autor:
Grnarova, P., Levy, K. Y., Aurelien Lucchi, Perraudin, N., Goodfellow, I., Hofmann, T., Krause, A.
Publikováno v:
Scopus-Elsevier
Generative Adversarial Networks (GANs) have shown remarkable results in modeling complex distributions, but their evaluation remains an unsettled issue. Evaluations are essential for: (i) relative assessment of different models and (ii) monitoring th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::160d155aa8a83f2b5c25da87df193c56
http://arxiv.org/abs/1811.05512
http://arxiv.org/abs/1811.05512
Publikováno v:
Scopus-Elsevier
Stochastic convex optimization is a basic and well studied primitive in machine learning. It is well known that convex and Lipschitz functions can be minimized efficiently using Stochastic Gradient Descent (SGD). The Normalized Gradient Descent (NGD)
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::606e71ce818cb28a64071e3d8c18bd9f
http://arxiv.org/abs/1507.02030
http://arxiv.org/abs/1507.02030
Publikováno v:
Scopus-Elsevier
The logistic loss function is often advocated in machine learning and statistics as a smooth and strictly convex surrogate for the 0-1 loss. In this paper we investigate the question of whether these smoothness and convexity properties make the logis
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d363c3708748bcf22a2a8d806cf83e2e
http://arxiv.org/abs/1405.3843
http://arxiv.org/abs/1405.3843
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
Scopus-Elsevier
DR-submodular continuous functions are important objectives with wide real-world applications spanning MAP inference in determinantal point processes (DPPs), and mean-field inference for probabilistic submodular models, amongst others. DR-submodulari
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::094fcff2ba504edc415ee9bc880bdd89
http://www.scopus.com/inward/record.url?eid=2-s2.0-85046993230&partnerID=MN8TOARS
http://www.scopus.com/inward/record.url?eid=2-s2.0-85046993230&partnerID=MN8TOARS