DITTO: Data-efficient and fair targeted subset selection for ASR accent adaptation

S Kothawade, A Mekala, M Kothyari, R Iyer… - arXiv preprint arXiv …, 2021 - arxiv.org
State-of-the-art Automatic Speech Recognition (ASR) systems are known to exhibit
disparate performance on varying speech accents. To improve performance on a specific …

Submodular Mutual Information for Targeted Data Subset Selection

S Kothawade, V Kaushal, G Ramakrishnan… - arXiv preprint arXiv …, 2021 - arxiv.org
With the rapid growth of data, it is becoming increasingly difficult to train or improve deep
learning models with the right subset of data. We show that this problem can be effectively …

Independence properties of generalized submodular information measures

H Asnani, J Bilmes, R Iyer - 2021 IEEE International …, 2021 - ieeexplore.ieee.org
Recently a class of generalized information measures was defined on sets of items
parametrized by submodular functions [7]. In this paper, we propose and study various …

A Unified Framework of Constrained Robust Submodular Optimization with Applications

R Iyer - arXiv preprint arXiv:1906.06393, 2019 - arxiv.org
Robust optimization is becoming increasingly important in machine learning applications. In
this paper, we study a unified framework of robust submodular optimization. We study this …