Zobrazeno 1 - 10
of 956
pro vyhledávání: '"Buet A"'
Autor:
Pagliari, Roberto, Hill, Peter, Chen, Po-Yu, Dabrowny, Maciej, Tan, Tingsheng, Buet-Golfouse, Francois
In financial applications, regulations or best practices often lead to specific requirements in machine learning relating to four key pillars: fairness, privacy, interpretability and greenhouse gas emissions. These all sit in the broader context of s
Externí odkaz:
http://arxiv.org/abs/2407.12445
Autor:
Tsai, Yu-Lin, Li, Yizhe, Chen, Zekai, Chen, Po-Yu, Yu, Chia-Mu, Ren, Xuebin, Buet-Golfouse, Francois
The integration of Differential Privacy (DP) with diffusion models (DMs) presents a promising yet challenging frontier, particularly due to the substantial memorization capabilities of DMs that pose significant privacy risks. Differential privacy off
Externí odkaz:
http://arxiv.org/abs/2406.01355
The advent of personalized content generation by LLMs presents a novel challenge: how to efficiently adapt text to meet individual preferences without the unsustainable demand of creating a unique model for each user. This study introduces an innovat
Externí odkaz:
http://arxiv.org/abs/2404.16115
Autor:
Buet, Blanche, Pennec, Xavier
By interpreting the product of the Principal Component Analysis, that is the covariance matrix, as a sequence of nested subspaces naturally coming with weights according to the level of approximation they provide, we are able to embed all $d$--dimens
Externí odkaz:
http://arxiv.org/abs/2305.10583
Publikováno v:
Mundo Agrario, Vol 25, Iss 59 (2024)
Este trabajo se propone cuantificar los cambios operados en el régimen de tenencia del suelo pampeano entre 1988 y 2018, y su imbricación con el proceso de concentración productiva regional, con énfasis en lo concerniente a la evolución más rec
Externí odkaz:
https://doaj.org/article/1824a4720d874476ba725317d20a4c9d
Autor:
Godeme, Jean-Jacques, Fadili, Jalal, Buet, Xavier, Zerrad, Myriam, Lequime, Michel, Amra, Claude
In this paper, we consider the problem of phase retrieval, which consists of recovering an $n$-dimensional real vector from the magnitude of its $m$ linear measurements. We propose a mirror descent (or Bregman gradient descent) algorithm based on a w
Externí odkaz:
http://arxiv.org/abs/2210.09248
Subtitles appear on screen as short pieces of text, segmented based on formal constraints (length) and syntactic/semantic criteria. Subtitle segmentation can be evaluated with sequence segmentation metrics against a human reference. However, standard
Externí odkaz:
http://arxiv.org/abs/2205.09360
As the amount of audio-visual content increases, the need to develop automatic captioning and subtitling solutions to match the expectations of a growing international audience appears as the only viable way to boost throughput and lower the related
Externí odkaz:
http://arxiv.org/abs/2205.06522
Autor:
Agrawal, Ashrya, Pfisterer, Florian, Bischl, Bernd, Buet-Golfouse, Francois, Sood, Srijan, Chen, Jiahao, Shah, Sameena, Vollmer, Sebastian
We present an empirical study of debiasing methods for classifiers, showing that debiasers often fail in practice to generalize out-of-sample, and can in fact make fairness worse rather than better. A rigorous evaluation of the debiasing treatment ef
Externí odkaz:
http://arxiv.org/abs/2011.02407
Autor:
Buet, Blanche, Rumpf, Martin
This paper investigates a discretization scheme for mean curvature motion on point cloud varifolds with particular emphasis on singular evolutions. To define the varifold a local covariance analysis is applied to compute an approximate tangent plane
Externí odkaz:
http://arxiv.org/abs/2010.09419