Zobrazeno 1 - 10
of 1 840
pro vyhledávání: '"Kalathil AN"'
Autor:
Bura, Archana, Bobbili, Sarat Chandra, Rameshkumar, Shreyas, Rengarajan, Desik, Kalathil, Dileep, Shakkottai, Srinivas
Media streaming is the dominant application over wireless edge (access) networks. The increasing softwarization of such networks has led to efforts at intelligent control, wherein application-specific actions may be dynamically taken to enhance the u
Externí odkaz:
http://arxiv.org/abs/2404.07315
Machine learning has shown great promise in addressing several critical hardware security problems. In particular, researchers have developed novel graph neural network (GNN)-based techniques for detecting intellectual property (IP) piracy, detecting
Externí odkaz:
http://arxiv.org/abs/2402.13946
This paper addresses the problem of Neural Network (NN) based adaptive stability certification in a dynamical system. The state-of-the-art methods, such as Neural Lyapunov Functions (NLFs), use NN-based formulations to assess the stability of a non-l
Externí odkaz:
http://arxiv.org/abs/2312.15340
Autor:
Kunde, Vishnu Teja, Rajagopalan, Vicram, Valmeekam, Chandra Shekhara Kaushik, Narayanan, Krishna, Shakkottai, Srinivas, Kalathil, Dileep, Chamberland, Jean-Francois
Pre-trained transformers exhibit the capability of adapting to new tasks through in-context learning (ICL), where they efficiently utilize a limited set of prompts without explicit model optimization. The canonical communication problem of estimating
Externí odkaz:
http://arxiv.org/abs/2311.00226
The goal of an offline reinforcement learning (RL) algorithm is to learn optimal polices using historical (offline) data, without access to the environment for online exploration. One of the main challenges in offline RL is the distribution shift whi
Externí odkaz:
http://arxiv.org/abs/2310.18434
Autor:
Ishfaq Showket Mir, Ali Riaz, Julie Fréchette, Joy Sankar Roy, James Mcelhinney, Sisi Pu, Hari Kalathil Balakrishnan, Jesse Greener, Ludovic F. Dumée, Younès Messaddeq
Publikováno v:
npj Clean Water, Vol 7, Iss 1, Pp 1-15 (2024)
Abstract Bacterial cellulose composites hold promise as renewable bioinspired materials for industrial and environmental applications. However, their use as free-standing water filtration membranes is hindered by low compressive strength, fouling, an
Externí odkaz:
https://doaj.org/article/01685408219d4323b1a686b9896ae5be
Can switching from cigarettes to heated tobacco products reduce consequences of pulmonary infection?
Publikováno v:
Respiratory Research, Vol 25, Iss 1, Pp 1-10 (2024)
Abstract Rationale While tobacco industry data suggests that switching from combustible cigarettes to heated tobacco products (HTPs), like IQOS, may reduce the users’ exposure to respiratory toxicants, it is not known if using HTPs impacts the outc
Externí odkaz:
https://doaj.org/article/31b98ae7e4654566a91684695bee78af
We study robust reinforcement learning (RL) with the goal of determining a well-performing policy that is robust against model mismatch between the training simulator and the testing environment. Previous policy-based robust RL algorithms mainly focu
Externí odkaz:
http://arxiv.org/abs/2307.08875
Autor:
Valmeekam, Chandra Shekhara Kaushik, Narayanan, Krishna, Kalathil, Dileep, Chamberland, Jean-Francois, Shakkottai, Srinivas
We provide new estimates of an asymptotic upper bound on the entropy of English using the large language model LLaMA-7B as a predictor for the next token given a window of past tokens. This estimate is significantly smaller than currently available e
Externí odkaz:
http://arxiv.org/abs/2306.04050
We consider the problem of federated offline reinforcement learning (RL), a scenario under which distributed learning agents must collaboratively learn a high-quality control policy only using small pre-collected datasets generated according to diffe
Externí odkaz:
http://arxiv.org/abs/2305.03097