Zobrazeno 1 - 10
of 650
pro vyhledávání: '"CHAWLA, SANJAY"'
Despite being a heavily researched topic, Adversarial Training (AT) is rarely, if ever, deployed in practical AI systems for two primary reasons: (i) the gained robustness is frequently accompanied by a drop in generalization and (ii) generating adve
Externí odkaz:
http://arxiv.org/abs/2405.17130
Autor:
Messaoud, Safa, Mokeddem, Billel, Xue, Zhenghai, Pang, Linsey, An, Bo, Chen, Haipeng, Chawla, Sanjay
Learning expressive stochastic policies instead of deterministic ones has been proposed to achieve better stability, sample complexity, and robustness. Notably, in Maximum Entropy Reinforcement Learning (MaxEnt RL), the policy is modeled as an expres
Externí odkaz:
http://arxiv.org/abs/2405.00987
Deep neural networks (DNNs) deployed in real-world applications can encounter out-of-distribution (OOD) data and adversarial examples. These represent distinct forms of distributional shifts that can significantly impact DNNs' reliability and robustn
Externí odkaz:
http://arxiv.org/abs/2404.05219
Large Language Models (LLM) have shown remarkable language capabilities fueling attempts to integrate them into applications across a wide range of domains. An important application area is question answering over private enterprise documents where t
Externí odkaz:
http://arxiv.org/abs/2402.07483
Autor:
Mokbel, Mohamed, Sakr, Mahmoud, Xiong, Li, Züfle, Andreas, Almeida, Jussara, Anderson, Taylor, Aref, Walid, Andrienko, Gennady, Andrienko, Natalia, Cao, Yang, Chawla, Sanjay, Cheng, Reynold, Chrysanthis, Panos, Fei, Xiqi, Ghinita, Gabriel, Graser, Anita, Gunopulos, Dimitrios, Jensen, Christian, Kim, Joon-Seok, Kim, Kyoung-Sook, Kröger, Peer, Krumm, John, Lauer, Johannes, Magdy, Amr, Nascimento, Mario, Ravada, Siva, Renz, Matthias, Sacharidis, Dimitris, Shahabi, Cyrus, Salim, Flora, Sarwat, Mohamed, Schoemans, Maxime, Speckmann, Bettina, Tanin, Egemen, Teng, Xu, Theodoridis, Yannis, Torp, Kristian, Trajcevski, Goce, van Kreveld, Marc, Wenk, Carola, Werner, Martin, Wong, Raymond, Wu, Song, Xu, Jianqiu, Youssef, Moustafa, Zeinalipour, Demetris, Zhang, Mengxuan, Zimányi, Esteban
Mobility data captures the locations of moving objects such as humans, animals, and cars. With the availability of GPS-equipped mobile devices and other inexpensive location-tracking technologies, mobility data is collected ubiquitously. In recent ye
Externí odkaz:
http://arxiv.org/abs/2307.05717
Adversarial training has been empirically shown to be more prone to overfitting than standard training. The exact underlying reasons still need to be fully understood. In this paper, we identify one cause of overfitting related to current practices o
Externí odkaz:
http://arxiv.org/abs/2211.16316
Autor:
Makke, Nour, Chawla, Sanjay
Symbolic regression is emerging as a promising machine learning method for learning succinct underlying interpretable mathematical expressions directly from data. Whereas it has been traditionally tackled with genetic programming, it has recently gai
Externí odkaz:
http://arxiv.org/abs/2211.10873
Adversarial training is widely acknowledged as the most effective defense against adversarial attacks. However, it is also well established that achieving both robustness and generalization in adversarially trained models involves a trade-off. The go
Externí odkaz:
http://arxiv.org/abs/2211.05523
Autor:
Chawla, Sanjay, Nakov, Preslav, Ali, Ahmed, Hall, Wendy, Khalil, Issa, Ma, Xiaosong, Sencar, Husrev Taha, Weber, Ingmar, Wooldridge, Michael, Yu, Ting
It is ten years since neural networks made their spectacular comeback. Prompted by this anniversary, we take a holistic perspective on Artificial Intelligence (AI). Supervised Learning for cognitive tasks is effectively solved - provided we have enou
Externí odkaz:
http://arxiv.org/abs/2210.01797
Autor:
Kunjir, Mayuresh, Chawla, Sanjay
Traffic signal control is an important problem in urban mobility with a significant potential of economic and environmental impact. While there is a growing interest in Reinforcement Learning (RL) for traffic signal control, the work so far has focus
Externí odkaz:
http://arxiv.org/abs/2201.02381