Zobrazeno 1 - 10
of 571
pro vyhledávání: '"Vicente Luís"'
Representation learning is an approach that allows to discover and extract the factors of variation from the data. Intuitively, a representation is said to be disentangled if it separates the different factors of variation in a way that is understand
Externí odkaz:
http://arxiv.org/abs/2408.07016
Autor:
Almudévar, Antonio, Mariotte, Théo, Ortega, Alfonso, Tahon, Marie, Vicente, Luis, Miguel, Antonio, Lleida, Eduardo
Prototypical Learning is based on the idea that there is a point (which we call prototype) around which the embeddings of a class are clustered. It has shown promising results in scenarios with little labeled data or to design explainable models. Typ
Externí odkaz:
http://arxiv.org/abs/2406.16145
In this paper, we examine team ball sports to investigate how the likelihood of weaker teams winning against stronger ones, referred to as underdog achievement, is influenced by inherent randomness factors that affect match outcomes in such sports. T
Externí odkaz:
http://arxiv.org/abs/2404.06626
We are interested in assessing the use of neural networks as surrogate models to approximate and minimize objective functions in optimization problems. While neural networks are widely used for machine learning tasks such as classification and regres
Externí odkaz:
http://arxiv.org/abs/2311.12253
Our goal is to give a purely algebraic characterization of finite abelian Galois covers of a complete, irreducible, non-singular curve $X$ over an algebraically closed field $\k$. To achieve this, we make use of the Galois theory of commutative rings
Externí odkaz:
http://arxiv.org/abs/2310.13443
Derivative-free optimization (DFO) consists in finding the best value of an objective function without relying on derivatives. To tackle such problems, one may build approximate derivatives, using for instance finite-difference estimates. One may als
Externí odkaz:
http://arxiv.org/abs/2310.00755
Autor:
Mingote, Victoria, Gimeno, Pablo, Vicente, Luis, Khurana, Sameer, Laurent, Antoine, Duret, Jarod
This paper proposes a direct text to speech translation system using discrete acoustic units. This framework employs text in different source languages as input to generate speech in the target language without the need for text transcriptions in thi
Externí odkaz:
http://arxiv.org/abs/2309.07478
Autor:
Khurana, Sameer, Dawalatabad, Nauman, Laurent, Antoine, Vicente, Luis, Gimeno, Pablo, Mingote, Victoria, Glass, James
Research in multilingual speech-to-text translation is topical. Having a single model that supports multiple translation tasks is desirable. The goal of this work it to improve cross-lingual transfer learning in multilingual speech-to-text translatio
Externí odkaz:
http://arxiv.org/abs/2306.00789
We consider the series $\sum_{n=1}^{\infty} z^{n} (a_{n} + x)^{-s}$ where $a_{n}$ satisfies a linear recurrence of arbitrary degree with integer coefficients. Under appropriate conditions, we prove that it can be continued to a meromorphic function o
Externí odkaz:
http://arxiv.org/abs/2303.16602
In this work, we propose different formulations and gradient-based algorithms for deterministic and stochastic bilevel problems with conflicting objectives in the lower level. Such problems have received little attention in the deterministic case and
Externí odkaz:
http://arxiv.org/abs/2302.05540