1 code implementation • 23 May 2024 • Divya Jyoti Bajpai, Manjesh Kumar Hanawal
Experimental results on five distinct datasets with BERT and ALBERT models demonstrate CeeBERT's ability to improve latency by reducing unnecessary computations with minimal drop in performance.
no code implementations • 23 Feb 2024 • Divya Jyoti Bajpai, Ayush Maheshwari, Manjesh Kumar Hanawal, Ganesh Ramakrishnan
The availability of large annotated data can be a critical bottleneck in training machine learning algorithms successfully, especially when applied to diverse domains.
1 code implementation • 19 Jan 2024 • Divya Jyoti Bajpai, Aastha Jaiswal, Manjesh Kumar Hanawal
The recent advances in Deep Neural Networks (DNNs) stem from their exceptional performance across various domains.
no code implementations • 30 Dec 2023 • Debamita Ghosh, Manjesh Kumar Hanawal, Nikola Zlatanova
To overcome this, {\it\HB} works with the discrete values of phase-shifting parameters and exploits their unimodal relations with channel gains to learn the optimal values faster.
no code implementations • 30 Apr 2023 • Fathima Zarin Faizal, Adway Girish, Manjesh Kumar Hanawal, Nikhil Karamchandani
We study the problem of best-arm identification in a distributed variant of the multi-armed bandit setting, with a central learner and multiple agents.
1 code implementation • 11 Apr 2021 • Atul Sahay, Ayush Maheshwari, Ritesh Kumar, Ganesh Ramakrishnan, Manjesh Kumar Hanawal, Kavi Arya
In this work, we propose an attention mechanism over Tree-LSTMs to learn more meaningful and explainable parse tree structures.
no code implementations • 15 Jun 2015 • Manjesh Kumar Hanawal, Venkatesh Saligrama, Michal Valko, R\' emi Munos
We consider stochastic sequential learning problems where the learner can observe the \textit{average reward of several actions}.