Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Sengupta, Shubho"'
Autor:
Kokolis, Apostolos, Kuchnik, Michael, Hoffman, John, Kumar, Adithya, Malani, Parth, Ma, Faye, DeVito, Zachary, Sengupta, Shubho, Saladi, Kalyan, Wu, Carole-Jean
Reliability is a fundamental challenge in operating large-scale machine learning (ML) infrastructures, particularly as the scale of ML models and training clusters continues to grow. Despite decades of research on infrastructure failures, the impact
Externí odkaz:
http://arxiv.org/abs/2410.21680
Autor:
Alshahwan, Nadia, Chheda, Jubin, Finegenova, Anastasia, Gokkaya, Beliz, Harman, Mark, Harper, Inna, Marginean, Alexandru, Sengupta, Shubho, Wang, Eddy
This paper describes Meta's TestGen-LLM tool, which uses LLMs to automatically improve existing human-written tests. TestGen-LLM verifies that its generated test classes successfully clear a set of filters that assure measurable improvement over the
Externí odkaz:
http://arxiv.org/abs/2402.09171
Autor:
Alshahwan, Nadia, Harman, Mark, Harper, Inna, Marginean, Alexandru, Sengupta, Shubho, Wang, Eddy
In this paper we address the following question: How can we use Large Language Models (LLMs) to improve code independently of a human, while ensuring that the improved code - does not regress the properties of the original code? - improves the origin
Externí odkaz:
http://arxiv.org/abs/2402.04380
Autor:
Fan, Angela, Gokkaya, Beliz, Harman, Mark, Lyubarskiy, Mitya, Sengupta, Shubho, Yoo, Shin, Zhang, Jie M.
This paper provides a survey of the emerging area of Large Language Models (LLMs) for Software Engineering (SE). It also sets out open research challenges for the application of LLMs to technical problems faced by software engineers. LLMs' emergent p
Externí odkaz:
http://arxiv.org/abs/2310.03533
Finite-state transducers (FSTs) are frequently used in speech recognition. Transducer composition is an essential operation for combining different sources of information at different granularities. However, composition is also one of the more comput
Externí odkaz:
http://arxiv.org/abs/2110.02848
Autor:
Knott, Brian, Venkataraman, Shobha, Hannun, Awni, Sengupta, Shubho, Ibrahim, Mark, van der Maaten, Laurens
Secure multi-party computation (MPC) allows parties to perform computations on data while keeping that data private. This capability has great potential for machine-learning applications: it facilitates training of machine-learning models on private
Externí odkaz:
http://arxiv.org/abs/2109.00984
Autor:
Movahedi, Mahnush, Case, Benjamin M., Knox, Andrew, Honaker, James, Li, Li, Li, Yiming Paul, Saravanan, Sanjay, Sengupta, Shubho, Taubeneck, Erik
In this paper, we outline a way to deploy a privacy-preserving protocol for multiparty Randomized Controlled Trials on the scale of 500 million rows of data and more than a billion gates. Randomized Controlled Trials (RCTs) are widely used to improve
Externí odkaz:
http://arxiv.org/abs/2101.04766
Contextual bandits are online learners that, given an input, select an arm and receive a reward for that arm. They use the reward as a learning signal and aim to maximize the total reward over the inputs. Contextual bandits are commonly used to solve
Externí odkaz:
http://arxiv.org/abs/1910.05299
Autor:
Tian, Yuandong, Ma, Jerry, Gong, Qucheng, Sengupta, Shubho, Chen, Zhuoyuan, Pinkerton, James, Zitnick, C. Lawrence
The AlphaGo, AlphaGo Zero, and AlphaZero series of algorithms are remarkable demonstrations of deep reinforcement learning's capabilities, achieving superhuman performance in the complex game of Go with progressively increasing autonomy. However, man
Externí odkaz:
http://arxiv.org/abs/1902.04522
Recurrent Neural Networks (RNN) are widely used to solve a variety of problems and as the quantity of data and the amount of available compute have increased, so have model sizes. The number of parameters in recent state-of-the-art networks makes the
Externí odkaz:
http://arxiv.org/abs/1704.05119