Výsledky vyhledávání - "Liva Ralaivola"

Akademický článek

Graph-based inter-subject pattern analysis of FMRI data.

Autor: Sylvain Takerkart, Guillaume Auzias, Bertrand Thirion, Liva Ralaivola

Publikováno v: PLoS ONE, Vol 9, Iss 8, p e104586 (2014)

In brain imaging, solving learning problems in multi-subjects settings is difficult because of the differences that exist across individuals. Here we introduce a novel classification framework based on group-invariant graphical representations, allow

Externí odkaz: https://doaj.org/article/2bec3e643d3e4fb1bd701b94f9021f70

Zobrazit plný text záznamu

Report

Decoy Bandits Dueling on a Poset

Autor: Audiffren, Julien, Liva, Ralaivola

We adress the problem of dueling bandits defined on partially ordered sets, or posets. In this setting, arms may not be comparable, and there may be several (incomparable) optimal arms. We propose an algorithm, UnchainedBandits, that efficiently find

Externí odkaz: http://arxiv.org/abs/1602.02706

Zobrazit plný text záznamu

QuicK-means: accelerating inference for K-means by learning fast transforms

Autor: Valentin Emiya, Liva Ralaivola, Hachem Kadri, Luc Giffon

Publikováno v: Machine Learning. 110:881-905

K-means—and the celebrated Lloyd’s algorithm—is more than the clustering method it was originally designed to be. It has indeed proven pivotal to help increase the speed of many machine learning, data analysis techniques such as indexing, neare

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::f77145e3285c0ddf5ad78a4321fbae13
https://doi.org/10.1007/s10994-021-05965-0

Zobrazit plný text záznamu

Recovery and Convergence Rate of the Frank–Wolfe Algorithm for the m-Exact-Sparse Problem

Autor: Valentin Emiya, Sandrine Anthoine, Liva Ralaivola, Farah Cherfaoui

Publikováno v: IEEE Transactions on Information Theory. 65:7407-7414

We study the properties of the Frank–Wolfe algorithm to solve the m-Exact-Sparse reconstruction problem, where a signal $y$ must be expressed as a sparse linear combination of a predefined set of atoms, called dictionary . We prove that when the si

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::d44db6d456f79ad78d005f8b0cc820f8
https://doi.org/10.1109/tit.2019.2919640

Zobrazit plný text záznamu

QuicK-means: Acceleration of K-means by learning a fast transform

Autor: Luc Giffon, Valentin Emiya, Hachem Kadri, Liva Ralaivola

Publikováno v: Machine Learning
Machine Learning, Springer Verlag, 2021, Machine Learning, 110, pp.881-905. ⟨10.1007/s10994-021-05965-0⟩
HAL
Machine Learning, 2021, Machine Learning, 110, pp.881-905. ⟨10.1007/s10994-021-05965-0⟩

International audience; K-means -- and the celebrated Lloyd algorithm -- is more than the clustering method it was originally designed to be. It has indeed proven pivotal to help increase the speed of many machine learning and data analysis technique

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::87c904d79552fb9a1fc8d3e65b1bf188
https://hal.archives-ouvertes.fr/hal-02174845

Zobrazit plný text záznamu

Partial Trace Regression and Low-Rank Kraus Decomposition

Autor: Hachem Kadri, Stéphane Ayache, Riikka Huusari, Alain Rakotomamonjy, Liva Ralaivola

Publikováno v: Aalto University
International Conference on Machine Learning
International Conference on Machine Learning, Jul 2020, Vienne, Austria
International Conference on Machine Learning, Jul 2020, Vienne (Online), Austria

International audience; The trace regression model, a direct extension of the well-studied linear regression model, allows one to map matrices to real-valued outputs. We here introduce an even more general model, namely the partial-trace regression m

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::820f0628b091b459100fdf155fd00b01
https://aaltodoc.aalto.fi/handle/123456789/107919

Zobrazit plný text záznamu

Recovery and convergence rate of the Frank-Wolfe Algorithm for the m-EXACT-SPARSE Problem

Autor: Farah Cherfaoui, Valentin Emiya, Liva Ralaivola, Sandrine Anthoine

Publikováno v: IEEE Transactions on Information Theory
IEEE Transactions on Information Theory, 2019, 65 (11)
IEEE Transactions on Information Theory, Institute of Electrical and Electronics Engineers, 2019, 65 (11)
HAL

International audience; We study the properties of the Frank-Wolfe algorithm to solve the m-EXACT-SPARSE reconstruction problem, where a signal y must be expressed as a sparse linear combination of a predefined set of atoms, called dictionary. We pro

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fa86ac56af68bfa0b92821ebea643b62
https://hal.science/hal-01919761v2/file/Franck_Wolfe_Cherfaoui_and_al_TIT.pdf

Zobrazit plný text záznamu

Frank-Wolfe Algorithm for the Exact Sparse Problem

Autor: Farah Cherfaoui, Valentin Emiya, Liva Ralaivola, Sandrine Anthoine

Publikováno v: iTWIST: international Traveling Workshop on Interactions between low-complexity data models and Sensing Techniques
iTWIST: international Traveling Workshop on Interactions between low-complexity data models and Sensing Techniques, Nov 2018, Marseille, France
HAL

International audience; In this paper, we study the properties of the Frank-Wolfe algorithm to solve the \ExactSparse reconstruction problem. We prove that when the dictionary is quasi-incoherent, at each iteration, the Frank-Wolfe algorithm picks up

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5bc37c52dc9a07d00a680d53f5bdb89c
https://hal-amu.archives-ouvertes.fr/hal-01881329/document

Zobrazit plný text záznamu

Online Learning of Task-specific Word Representations with a Joint Biconvex Passive-Aggressive Algorithm

Autor: Liva Ralaivola, Pascal Denis

Publikováno v: European Chapter of the Association for Computational Linguistics
European Chapter of the Association for Computational Linguistics, Apr 2017, Valencia, Spain. pp.775-784, ⟨10.18653/v1/E17-1073⟩
EACL (1)

International audience; This paper presents a new, efficient method for learning task-specific word vectors using a variant of the Passive-Aggressive algorithm. Specifically, this algorithm learns a word embedding matrix in tandem with the classifier

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b1a636c124a9614b511f234079e19798
https://inria.hal.science/hal-01590594

Zobrazit plný text záznamu

Risk Upper Bounds for General Ensemble Methods with an application to Multiclass Classification

Autor: Liva Ralaivola, Emilie Morvant, Jean-Francis Roy, François Laviolette

Publikováno v: Neurocomputing
Neurocomputing, Elsevier, 2017, 219, pp.15-25. ⟨10.1016/j.neucom.2016.09.016⟩
Neurocomputing, 2017, 219, pp.15-25. ⟨10.1016/j.neucom.2016.09.016⟩

Published version: http://www.sciencedirect.com/science/article/pii/S0925231216310177; International audience; This paper generalizes a pivotal result from the PAC-Bayesian literature ---the C-bound--- primarily designed for binary classification to

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e0bae2a88fb6f8d5a70ff7809675d0de
https://hal.archives-ouvertes.fr/hal-01363293

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání