Zobrazeno 1 - 10
of 575
pro vyhledávání: '"Moulin, Pierre A."'
Autor:
Grahammer, Florian, Dumoulin, Bernhard, Gulieva, Ramila E., Wu, Hui, Xu, Yaoxian, Sulaimanov, Nurgazy, Arnold, Frederic, Sandner, Lukas, Cordts, Tomke, Todkar, Abhijeet, Moulin, Pierre, Reichardt, Wilfried, Puelles, Victor G., Kramann, Rafael, Freedman, Benjamin S., Busch, Hauke, Boerries, Melanie, Walz, Gerd, Huber, Tobias B.
Publikováno v:
In Kidney International November 2024 106(5):856-869
Autor:
Goel, Amish, Moulin, Pierre
Deep learning image classifiers are known to be vulnerable to small adversarial perturbations of input images. In this paper, we derive the locally optimal generalized likelihood ratio test (LO-GLRT) based detector for detecting stochastic targeted u
Externí odkaz:
http://arxiv.org/abs/2012.04692
Robust machine learning formulations have emerged to address the prevalent vulnerability of deep neural networks to adversarial examples. Our work draws the connection between optimal robust learning and the privacy-utility tradeoff problem, which is
Externí odkaz:
http://arxiv.org/abs/2007.11693
Various adversarial audio attacks have recently been developed to fool automatic speech recognition (ASR) systems. We here propose a defense against such attacks based on the uncertainty introduced by dropout in neural networks. We show that our defe
Externí odkaz:
http://arxiv.org/abs/2006.01906
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Yu, Xi, Smedemark-Margulies, Niklas, Aeron, Shuchin, Koike-Akino, Toshiaki, Moulin, Pierre, Brand, Matthew, Parsons, Kieran, Wang, Ye
Publikováno v:
In Pattern Recognition February 2023 134
Autor:
Johnstone, Patrick R., Moulin, Pierre
Publikováno v:
Math. Program. 180, 417-450 (2020)
The purpose of this manuscript is to derive new convergence results for several subgradient methods applied to minimizing nonsmooth convex functions with H\"olderian growth. The growth condition is satisfied in many applications and includes function
Externí odkaz:
http://arxiv.org/abs/1704.00196
Autor:
Johnstone, Patrick R., Moulin, Pierre
We study the convergence properties of a general inertial first-order proximal splitting algorithm for solving nonconvex nonsmooth optimization problems. Using the Kurdyka--\L ojaziewicz (KL) inequality we establish new convergence rates which apply
Externí odkaz:
http://arxiv.org/abs/1609.03626
Let $X_i, i \in V$ form a Markov random field (MRF) represented by an undirected graph $G = (V,E)$, and $V'$ be a subset of $V$. We determine the smallest graph that can always represent the subfield $X_i, i \in V'$ as an MRF. Based on this result, w
Externí odkaz:
http://arxiv.org/abs/1608.03697
Hashing has emerged as a popular technique for large-scale similarity search. Most learning-based hashing methods generate compact yet correlated hash codes. However, this redundancy is storage-inefficient. Hence we propose a lossless variable-length
Externí odkaz:
http://arxiv.org/abs/1603.05414