Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Sukthanker, Rhea Sanjay"'
Autor:
Sukthanker, Rhea Sanjay, Zela, Arber, Staffler, Benedikt, Klein, Aaron, Purucker, Lennart, Franke, Joerg K. H., Hutter, Frank
The increasing size of language models necessitates a thorough analysis across multiple dimensions to assess trade-offs among crucial hardware metrics such as latency, energy consumption, GPU memory usage, and performance. Identifying optimal model c
Externí odkaz:
http://arxiv.org/abs/2405.10299
Autor:
Sukthanker, Rhea Sanjay, Zela, Arber, Staffler, Benedikt, Dooley, Samuel, Grabocka, Josif, Hutter, Frank
Pareto front profiling in multi-objective optimization (MOO), i.e. finding a diverse set of Pareto optimal solutions, is challenging, especially with expensive objectives like neural network training. Typically, in MOO neural architecture search (NAS
Externí odkaz:
http://arxiv.org/abs/2402.18213
Weight sharing is a fundamental concept in neural architecture search (NAS), enabling gradient-based methods to explore cell-based architecture spaces significantly faster than traditional blackbox approaches. In parallel, weight \emph{entanglement}
Externí odkaz:
http://arxiv.org/abs/2312.10440
Autor:
Dooley, Samuel, Sukthanker, Rhea Sanjay, Dickerson, John P., White, Colin, Hutter, Frank, Goldblum, Micah
Face recognition systems are widely deployed in safety-critical applications, including law enforcement, yet they exhibit bias across a range of socio-demographic dimensions, such as gender and race. Conventional wisdom dictates that model biases ari
Externí odkaz:
http://arxiv.org/abs/2210.09943
Flow-based generative models have shown an excellent ability to explicitly learn the probability density function of data via a sequence of invertible transformations. Yet, learning attentions in generative flows remains understudied, while it has ma
Externí odkaz:
http://arxiv.org/abs/2106.03959
Autor:
Wu, Yan, Huang, Zhiwu, Kumar, Suryansh, Sukthanker, Rhea Sanjay, Timofte, Radu, Van Gool, Luc
Modern solutions to the single image super-resolution (SISR) problem using deep neural networks aim not only at better performance accuracy but also at a lighter and computationally efficient model. To that end, recently, neural architecture search (
Externí odkaz:
http://arxiv.org/abs/2101.06658
Autor:
Sukthanker, Rhea Sanjay, Huang, Zhiwu, Kumar, Suryansh, Endsjo, Erik Goron, Wu, Yan, Van Gool, Luc
In this paper, we propose a new neural architecture search (NAS) problem of Symmetric Positive Definite (SPD) manifold networks, aiming to automate the design of SPD neural architectures. To address this problem, we first introduce a geometrically ri
Externí odkaz:
http://arxiv.org/abs/2010.14535