Zobrazeno 1 - 10
of 148
pro vyhledávání: '"Jegelka S"'
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Suau de Castro, M., He, J., Spaan, M.T.J., Oliehoek, F.A., Chaudhuri, K., Jegelka, S., Song, L., Szepesvari, C., Niu, G., Sabato, S.
Publikováno v:
Proceedings of the 39th International Conference on Machine Learning, 162
Learning effective policies for real-world problems is still an open challenge for the field of reinforcement learning (RL). The main limitation being the amount of data needed and the pace at which that data can be obtained. In this paper, we study
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=narcis______::64c15b37f07a967ff1857af5d9157cb6
http://resolver.tudelft.nl/uuid:ec39b987-ac99-4fa3-92f4-f25006505d50
http://resolver.tudelft.nl/uuid:ec39b987-ac99-4fa3-92f4-f25006505d50
Publikováno v:
Scopus-Elsevier
Optimal Transport has recently gained interest in machine learning for applications ranging from domain adaptation, sentence similarities to deep learning. Yet, its ability to capture frequently occurring structure beyond the "ground metric" is limit
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::259cad4434d44363172a91aab860a33f
http://arxiv.org/abs/1712.06199
http://arxiv.org/abs/1712.06199
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
Research on distributed machine learning algorithms has focused primarily on one of two extremes - algorithms that obey strict concurrency constraints or algorithms that obey few or no such constraints. We consider an intermediate alternative in whic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::70c1eea2f80423ed84352c10aa749ef3
http://arxiv.org/abs/1307.8049
http://arxiv.org/abs/1307.8049
Publikováno v:
Advances in Neural Information Processing Systems 24
We are motivated by an application to extract a representative subset of machine learning training data and by the poor empirical performance we observe of the popular minimum norm algorithm. In fact, for our application, minimum norm can have a runn
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______1874::1ee2b830f80b7a69168119462d3bc66e
https://hdl.handle.net/11858/00-001M-0000-0013-B880-6
https://hdl.handle.net/11858/00-001M-0000-0013-B880-6
Autor:
Jegelka, S., Bilmes, J.
Publikováno v:
NIPS 2010 Workshop on Discrete Optimization in Machine Learning: Structures, Algorithms and Applications (DISCML)
Building on recent results for submodular minimization with combinatorial constraints, and on online submodular minimization, we address online approximation algorithms for submodular minimization with combinatorial constraints. We discuss two types
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______1874::e61a0591224f3df475667f1a4ae3e598
https://hdl.handle.net/11858/00-001M-0000-0013-BD38-F21.11116/0000-0002-7E52-5
https://hdl.handle.net/11858/00-001M-0000-0013-BD38-F21.11116/0000-0002-7E52-5
Autor:
Jegelka, S., Bilmes, J.
Publikováno v:
UWEE Technical Report
We propose a novel framework for graph-based cooperative regularization that uses submodular costs on graph edges. We introduce an efficient iterative algorithm to solve the resulting hard discrete optimization problem, and show that it has a guarant
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______1874::94c73264b8704a6999efffac244a4d18
https://hdl.handle.net/11858/00-001M-0000-0013-BECE-6
https://hdl.handle.net/11858/00-001M-0000-0013-BECE-6
Autor:
Jegelka, S., Bilmes, J.
Publikováno v:
Technical Report of the Max Planck Institute for Biological Cybernetics
We introduce a problem we call Cooperative cut, where the goal is to find a minimum-cost graph cut but where a submodular function is used to define the cost of a subsets of edges. That means, the cost of an edge that is added to the current cut set
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______1874::8472334af6546da0047953e30f7b6475
https://hdl.handle.net/21.11116/0000-0002-8598-C11858/00-001M-0000-0013-C10A-9
https://hdl.handle.net/21.11116/0000-0002-8598-C11858/00-001M-0000-0013-C10A-9