Zobrazeno 1 - 10
of 26 820
pro vyhledávání: '"MOKHTARI, A."'
Autor:
Mokhtari, Melvin
As the field of data analysis grows rapidly due to the large amounts of data being generated, effective data classification has become increasingly important. This paper introduces the RUle Mutation Classifier (RUMC), which represents a significant i
Externí odkaz:
http://arxiv.org/abs/2412.07885
We study the problem of finding an $\epsilon$-first-order stationary point (FOSP) of a smooth function, given access only to gradient information. The best-known gradient query complexity for this task, assuming both the gradient and Hessian of the o
Externí odkaz:
http://arxiv.org/abs/2412.02175
Medical imaging has significantly revolutionized medical diagnostics and treatment planning, progressing from early X-ray usage to sophisticated methods like MRIs, CT scans, and ultrasounds. This paper investigates the use of deep learning for medica
Externí odkaz:
http://arxiv.org/abs/2411.14039
Autor:
Libourel, Guy, Mokhtari, Marwane, Rohani, Vandad-Julien, Bourdon, Bernard, Ganino, Clément, Lagadec, Eric, Vennéguès, Philippe, Guigoz, Vincent, Cauneau, François, Fulcheri, Laurent
Publikováno v:
2024NatAs.tmp..260L
Condensation processes, which are responsible for the main chemical differences between gas and solids in the Galaxy, are the major mechanisms that control the cycle of dust from evolved stars to planetary systems. However, they are still poorly unde
Externí odkaz:
http://arxiv.org/abs/2411.11529
Mixtures of Experts (MoE) are Machine Learning models that involve partitioning the input space, with a separate "expert" model trained on each partition. Recently, MoE have become popular as components in today's large language models as a means to
Externí odkaz:
http://arxiv.org/abs/2411.06056
Autor:
Block, Jacob L., Srinivasan, Sundararajan, Collins, Liam, Mokhtari, Aryan, Shakkottai, Sanjay
The power of foundation models (FMs) lies in their capacity to learn highly expressive representations that can be adapted to a broad spectrum of tasks. However, these pretrained models require multiple stages of fine-tuning to become effective for d
Externí odkaz:
http://arxiv.org/abs/2410.22264
This work revisits the classical low-rank matrix factorization problem and unveils the critical role of initialization in shaping convergence rates for such nonconvex and nonsmooth optimization. We introduce Nystrom initialization, which significantl
Externí odkaz:
http://arxiv.org/abs/2410.18965
Optimal transport on a graph focuses on finding the most efficient way to transfer resources from one distribution to another while considering the graph's structure. This paper introduces a new distributed algorithm that solves the optimal transport
Externí odkaz:
http://arxiv.org/abs/2410.05509
The electrical network reconfiguration problem aims to minimize losses in a distribution system by adjusting switches while ensuring radial topology. The growing use of renewable energy and the complexity of managing modern power grids make solving t
Externí odkaz:
http://arxiv.org/abs/2410.04604
Autor:
Jiang, Ruichen, Mokhtari, Aryan
In this paper, we propose a quasi-Newton method for solving smooth and monotone nonlinear equations, including unconstrained minimization and minimax optimization as special cases. For the strongly monotone setting, we establish two global convergenc
Externí odkaz:
http://arxiv.org/abs/2410.02626