Zobrazeno 1 - 10
of 201
pro vyhledávání: '"Gupta, Arushi"'
With LLMs shifting their role from statistical modeling of language to serving as general-purpose AI agents, how should LLM evaluations change? Arguably, a key ability of an AI agent is to flexibly combine, as needed, the basic skills it has learned.
Externí odkaz:
http://arxiv.org/abs/2310.17567
We investigate robust model-free reinforcement learning algorithms designed for environments that may be dynamic or even adversarial. Traditional state-based policies often struggle to accommodate the challenges imposed by the presence of unmodeled d
Externí odkaz:
http://arxiv.org/abs/2305.17552
Saliency methods compute heat maps that highlight portions of an input that were most {\em important} for the label assigned to it by a deep net. Evaluations of saliency methods convert this heat map into a new {\em masked input} by retaining the $k$
Externí odkaz:
http://arxiv.org/abs/2211.02912
Influence functions estimate effect of individual data points on predictions of the model on test data and were adapted to deep learning in Koh and Liang [2017]. They have been used for detecting data poisoning, detecting helpful and harmful examples
Externí odkaz:
http://arxiv.org/abs/2210.01072
Research on generalization bounds for deep networks seeks to give ways to predict test error using just the training dataset and the network parameters. While generalization bounds can give many insights about architecture design, training algorithms
Externí odkaz:
http://arxiv.org/abs/2111.14212
An effective approach in meta-learning is to utilize multiple "train tasks" to learn a good initialization for model parameters that can help solve unseen "test tasks" with very few samples by fine-tuning from this initialization. Although successful
Externí odkaz:
http://arxiv.org/abs/2106.15615
Autor:
Gupta, Arushi
To understand requirements traceability in practice, we present a preliminary study of identifying questions from requirements repositories and examining their answering status. Investigating 345 open-source projects results in 20,622 requirements qu
Autor:
Gupta, Arushi
Previous work has examined the ability of larger capacity neural networks to generalize better than smaller ones, even without explicit regularizers, by analyzing gradient based algorithms such as GD and SGD. The presence of noise and its effect on r
Externí odkaz:
http://arxiv.org/abs/2005.12743
Publikováno v:
In Trends in Anaesthesia and Critical Care December 2023 53
Autor:
Singh, Simarjeet, Walia, Nidhi, Bekiros, Stelios, Gupta, Arushi, Kumar, Jigyasu, Mishra, Amar Kumar
Publikováno v:
Journal of Economics, Finance and Administrative Science, 2022, Vol. 27, Issue 54, pp. 328-343.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/JEFAS-08-2021-0159