1 code implementation • 30 May 2024 • Vijay Lingam, Atula Tejaswi, Aditya Vavre, Aneesh Shetty, Gautham Krishna Gudur, Joydeep Ghosh, Alex Dimakis, Eunsol Choi, Aleksandar Bojchevski, Sujay Sanghavi
Extensive experiments on language and vision benchmarks show that SVFT recovers up to 96% of full fine-tuning performance while training only 0. 006 to 0. 25% of parameters, outperforming existing methods that only recover up to 85% performance using 0. 03 to 0. 8% of the trainable parameter budget.
no code implementations • 12 Oct 2022 • Ganesh Tata, Gautham Krishna Gudur, Gopinath Chennupati, Mohammad Emtiyaz Khan
Calibration can reduce overconfident predictions of deep neural networks, but can calibration also accelerate training?
no code implementations • 18 Jun 2021 • Gautham Krishna Gudur, Satheesh K. Perepu
Federated learning is an effective way of extracting insights from different user devices while preserving the privacy of users.
no code implementations • 4 Dec 2020 • Gautham Krishna Gudur, Satheesh K. Perepu
Such applications demand characterization of insights from multiple resource-constrained user devices using machine learning techniques for effective personalized activity monitoring.
no code implementations • 4 Dec 2020 • Abhijith Ragav, Gautham Krishna Gudur
In the recent past, psychological stress has been increasingly observed in humans, and early detection is crucial to prevent health risks.
no code implementations • 6 Nov 2020 • Gautham Krishna Gudur, Bala Shyamala Balaji, Satheesh K. Perepu
In addition, in this paper we explore a new challenge of interest -- to handle label heterogeneities in federated learning.
1 code implementation • 31 May 2019 • Gautham Krishna Gudur, Prahalathan Sundaramoorthy, Venkatesh Umaashankar
Various health-care applications such as assisted living, fall detection etc., require modeling of user behavior through Human Activity Recognition (HAR).