no code implementations • 11 Apr 2024 • Pranav Narayanan Venkit, Tatiana Chakravorti, Vipul Gupta, Heidi Biggs, Mukund Srinath, Koustava Goswami, Sarah Rajtmajer, Shomir Wilson
We investigate how hallucination in large language models (LLM) is characterized in peer-reviewed literature using a critical examination of 103 publications across NLP research.
no code implementations • 6 Feb 2024 • Sandipp Krishnan Ravi, Yigitcan Comlek, Wei Chen, Arjun Pathak, Vipul Gupta, Rajnikant Umretiya, Andrew Hoffman, Ghanshyam Pilania, Piyush Pandita, Sayan Ghosh, Nathaniel Mckeever, Liping Wang
Towards resolving this issue, a multi-source data fusion framework based on Latent Variable Gaussian Process (LVGP) is proposed.
no code implementations • 18 Oct 2023 • Pranav Narayanan Venkit, Mukund Srinath, Sanjana Gautam, Saranya Venkatraman, Vipul Gupta, Rebecca J. Passonneau, Shomir Wilson
We conduct an inquiry into the sociotechnical aspects of sentiment analysis (SA) by critically examining 189 peer-reviewed papers on their applications, models, and datasets.
1 code implementation • 24 Aug 2023 • Vipul Gupta, Pranav Narayanan Venkit, Hugo Laurençon, Shomir Wilson, Rebecca J. Passonneau
We apply CALM to 20 large language models, and find that for 2 language model series, larger parameter models tend to be more biased than smaller ones.
no code implementations • 17 Aug 2023 • Harsh Raj, Vipul Gupta, Domenic Rosati, Subhabrata Majumdar
Large Language Models (LLMs) exhibit remarkable fluency and competence across various natural language tasks.
no code implementations • 13 Jun 2023 • Vipul Gupta, Pranav Narayanan Venkit, Shomir Wilson, Rebecca J. Passonneau
This paper presents a comprehensive survey of work on sociodemographic bias in language models (LMs).
no code implementations • 10 Mar 2023 • Vipul Gupta, Apurva Narayan
We show that we can decrease the training time for any adversarial training algorithm by using only a subset of training data for adversarial training.
1 code implementation • CVPR 2022 • Vipul Gupta, Zhuowan Li, Adam Kortylewski, Chenyu Zhang, Yingwei Li, Alan Yuille
By swapping the context object features, the model reliance on context can be suppressed effectively.
no code implementations • 16 May 2021 • Vipul Gupta, Avishek Ghosh, Michal Derezinski, Rajiv Khanna, Kannan Ramchandran, Michael Mahoney
To enhance practicability, we devise an adaptive scheme to choose L, and we show that this reduces the number of local iterations in worker machines between two model synchronizations as the training proceeds, successively refining the model quality at the master.
1 code implementation • 26 Oct 2020 • Amirali Aghazadeh, Vipul Gupta, Alex DeWeese, O. Ozan Koyluoglu, Kannan Ramchandran
We consider feature selection for applications in machine learning where the dimensionality of the data is so large that it exceeds the working memory of the (local) computing machine.
no code implementations • 18 Oct 2020 • Vipul Gupta, Dhruv Choudhary, Ping Tak Peter Tang, Xiaohan Wei, Xing Wang, Yuzhen Huang, Arun Kejariwal, Kannan Ramchandran, Michael W. Mahoney
This is done by identifying and updating only the most relevant neurons of the neural network for each training sample in the data.
1 code implementation • 18 Aug 2020 • Vipul Gupta, Soham Phade, Thomas Courtade, Kannan Ramchandran
As one of the fastest-growing cloud services, serverless computing provides an opportunity to better serve both users and providers through the incorporation of market-based strategies for pricing and resource allocation.
Distributed, Parallel, and Cluster Computing Computer Science and Game Theory
1 code implementation • 21 Jan 2020 • Vipul Gupta, Dominic Carrano, Yaoqing Yang, Vaishaal Shankar, Thomas Courtade, Kannan Ramchandran
Inexpensive cloud services, such as serverless computing, are often vulnerable to straggling nodes that increase end-to-end latency for distributed computation.
Distributed, Parallel, and Cluster Computing Information Theory Information Theory
no code implementations • ICLR 2020 • Vipul Gupta, Santiago Akle Serrano, Dennis Decoste
We propose Stochastic Weight Averaging in Parallel (SWAP), an algorithm to accelerate DNN training.
1 code implementation • 21 Mar 2019 • Vipul Gupta, Swanand Kadhe, Thomas Courtade, Michael W. Mahoney, Kannan Ramchandran
Motivated by recent developments in serverless systems for large-scale computation as well as improvements in scalable randomized matrix algorithms, we develop OverSketched Newton, a randomized Hessian-based optimization algorithm to solve large-scale convex optimization problems in serverless systems.
1 code implementation • 6 Nov 2018 • Vipul Gupta, Shusen Wang, Thomas Courtade, Kannan Ramchandran
We propose OverSketch, an approximate algorithm for distributed matrix multiplication in serverless computing.
Distributed, Parallel, and Cluster Computing Information Theory Information Theory
no code implementations • 24 Oct 2017 • Jingge Zhu, Ye Pu, Vipul Gupta, Claire Tomlin, Kannan Ramchandran
As an application of the results, we demonstrate solving optimization problems using a sequential approximation approach, which accelerates the algorithm in a distributed system with stragglers.