no code implementations • 26 Sep 2022 • Surya Kant Sahu
Meta-Learning has emerged as a research direction to better transfer knowledge from related tasks to unseen but related tasks.
no code implementations • 16 Jun 2022 • Surya Kant Sahu, Sai Mitheran, Somya Suhans Mahapatra
The Lottery Ticket Hypothesis (LTH) states that for a reasonably sized neural network, a sub-network within the same network yields no less performance than the dense counterpart when trained from the same initialization.
no code implementations • 2 Dec 2021 • Ayush Chopra, Surya Kant Sahu, Abhishek Singh, Abhinav Java, Praneeth Vepakomma, Vivek Sharma, Ramesh Raskar
In this work, we introduce AdaSplit which enables efficiently scaling SL to low resource scenarios by reducing bandwidth consumption and improving performance across heterogeneous clients.
no code implementations • Submitted to NeurIPS 2021 ENLSP Workshop 2021 • Surya Kant Sahu, Sai Mitheran, Juhi Kamdar, Meet Gandhi
Transformers have seen an unprecedented rise in Natural Language Processing and Computer Vision tasks.
1 code implementation • 4 Jul 2021 • Sai Mitheran, Abhinav Java, Surya Kant Sahu, Arshad Shaikh
Session-based recommendation systems suggest relevant items to users by modeling user behavior and preferences using short-term anonymous sessions.
Ranked #5 on Session-Based Recommendations on yoochoose1/64
no code implementations • 5 Feb 2021 • Surya Kant Sahu, Abhinav Java, Arshad Shaikh, Yannic Kilcher
To that end, we first define a metric, MLH (Model Enthalpy), that measures the closeness of a set of numbers to Benford's Law and we show empirically that it is a strong predictor of Validation Accuracy.