Zobrazeno 1 - 10
of 3 892
pro vyhledávání: '"Bruss, A."'
Autor:
Stein, Alex, Sharpe, Samuel, Bergman, Doron, Kumar, Senthil, Bruss, Bayan, Dickerson, John, Goldstein, Tom, Goldblum, Micah
Many real-world applications of tabular data involve using historic events to predict properties of new ones, for example whether a credit card transaction is fraudulent or what rating a customer will assign a product on a retail platform. Existing a
Externí odkaz:
http://arxiv.org/abs/2410.10648
Autor:
Potapczynski, Andres, Qiu, Shikai, Finzi, Marc, Ferri, Christopher, Chen, Zixi, Goldblum, Micah, Bruss, Bayan, De Sa, Christopher, Wilson, Andrew Gordon
Dense linear layers are the dominant computational bottleneck in large neural networks, presenting a critical need for more efficient alternatives. Previous efforts focused on a small number of hand-crafted structured matrices and neglected to invest
Externí odkaz:
http://arxiv.org/abs/2410.02117
Publikováno v:
ACM AI in Finance Conference ICAIF 2024
Adoption of AI by criminal entities across traditional and emerging financial crime paradigms has been a disturbing recent trend. Particularly concerning is the proliferation of generative AI, which has empowered criminal activities ranging from soph
Externí odkaz:
http://arxiv.org/abs/2410.09066
This work explores the important role of quantum routers in communication networks and investigates the increase in efficiency using memories and multiplexing strategies. Motivated by the bipartite setup introduced by Abruzzo et al. (2013) for finite
Externí odkaz:
http://arxiv.org/abs/2406.13492
Autor:
Shwartz-Ziv, Ravid, Goldblum, Micah, Bansal, Arpit, Bruss, C. Bayan, LeCun, Yann, Wilson, Andrew Gordon
It is widely believed that a neural network can fit a training set containing at least as many samples as it has parameters, underpinning notions of overparameterized and underparameterized models. In practice, however, we only find solutions accessi
Externí odkaz:
http://arxiv.org/abs/2406.11463
Autor:
Beige, Almut, Predojević, Ana, Metelmann, Anja, Sanpera, Anna, Macchiavello, Chiara, Koch, Christiane P., Silberhorn, Christine, Toninelli, Costanza, Bruß, Dagmar, Ercolessi, Elisa, Paladino, Elisabetta, Ferlaino, Francesca, Ferrini, Giulia, Platero, Gloria, Fuentes, Ivette, Nemoto, Kae, Tarruell, Leticia, Bondani, Maria, Chiofalo, Marilu, Pons, Marisa, D'Angelo, Milena, Murao, Mio, Fabbri, Nicole, Verrucchi, Paola, Senellart-Mardon, Pascale, Citro, Roberta, Zambrini, Roberta, González-Férez, Rosario, Maniscalco, Sabrina, Huelga, Susana, Mehlstäubler, Tanja, Parigi, Valentina, Ahufinger, Verónica
Data show that the presence of women in quantum science is affected by a number of detriments and their percentage decreases even further for higher positions. Beyond data, from our shared personal experiences as female tenured quantum physics profes
Externí odkaz:
http://arxiv.org/abs/2407.02612
Autor:
Aldous, David J., Bruss, F. Thomas
Publikováno v:
A final version is published as {\em Amer. Math. Monthly} 130 (2023) 303--320
We give elementary examples within a framework for studying decisions under uncertainty where probabilities are only roughly known. The framework, in gambling terms, is that the size of a bet is proportional to the gambler's perceived advantage based
Externí odkaz:
http://arxiv.org/abs/2312.10331
Autor:
Bruss, F. Thomas
{\bf Abstract.} The present article is an essay about mathematical intuition and Artificial intelligence (A.I.), followed by a guided excursion to a well-known open problem. It has two objectives. The first is to reconcile the way of thinking of a co
Externí odkaz:
http://arxiv.org/abs/2401.05368
Real-world datasets are often highly class-imbalanced, which can adversely impact the performance of deep learning models. The majority of research on training neural networks under class imbalance has focused on specialized loss functions, sampling
Externí odkaz:
http://arxiv.org/abs/2312.02517
Autor:
Cherepanova, Valeriia, Levin, Roman, Somepalli, Gowthami, Geiping, Jonas, Bruss, C. Bayan, Wilson, Andrew Gordon, Goldstein, Tom, Goldblum, Micah
Publikováno v:
Conference on Neural Information Processing Systems 2023
Academic tabular benchmarks often contain small sets of curated features. In contrast, data scientists typically collect as many features as possible into their datasets, and even engineer new features from existing ones. To prevent overfitting in su
Externí odkaz:
http://arxiv.org/abs/2311.05877