166 citations · 515 across the 60 of their papers we have counts for
9 papers · 1 filter
Speeding up NAS with Adaptive Subset Selection
Vishak Prasad C, Colin White, Paarth Jain +2
A majority of recent developments in neural architecture search (NAS) have been aimed at decreasing the computational cost of various techniques without affecting their final perfo…
Partitioned Gradient Matching-based Data Subset Selection for Compute-Efficient Robust ASR Training
Ashish Mittal, Durga Sivasubramanian, Rishabh Iyer +2
Training state-of-the-art ASR systems such as RNN-T often has a high associated financial and environmental cost. Training with a subset of training data could mitigate this proble…
DIAGNOSE: Avoiding Out-of-distribution Data using Submodular Information Measures
Suraj Kothawade, Akshit Srivastava, Venkat Iyer +2
Avoiding out-of-distribution (OOD) data is critical for training supervised machine learning models in the medical imaging domain. Furthermore, obtaining labeled medical data is di…
CLINICAL: Targeted Active Learning for Imbalanced Medical Image Classification
Suraj Kothawade, Atharv Savarkar, Venkat Iyer +3
Training deep learning models on medical datasets that perform well for all classes is a challenging task. It is often the case that a suboptimal performance is obtained on some cl…
Active Data Discovery: Mining Unknown Data using Submodular Information Measures
Suraj Kothawade, Shivang Chopra, Saikat Ghosh +1
Active Learning is a very common yet powerful framework for iteratively and adaptively sampling subsets of the unlabeled sets with a human in the loop with the goal of achieving la…
AUTOMATA: Gradient Based Data Subset Selection for Compute-Efficient Hyper-parameter Tuning
Krishnateja Killamsetty, Guttu Sai Abhishek, Aakriti +4
Deep neural networks have seen great success in recent years; however, training a deep model is often challenging as its performance heavily depends on the hyper-parameters used. I…
BASIL: Balanced Active Semi-supervised Learning for Class Imbalanced Datasets
Suraj Kothawade, Pavan Kumar Reddy, Ganesh Ramakrishnan +1
Current semi-supervised learning (SSL) methods assume a balance between the number of data points available for each class in both the labeled and the unlabeled data sets. However,…
Submodlib: A Submodular Optimization Library
Vishal Kaushal, Ganesh Ramakrishnan, Rishabh Iyer
Submodular functions are a special class of set functions which naturally model the notion of representativeness, diversity, coverage etc. and have been shown to be computationally…
PLATINUM: Semi-Supervised Model Agnostic Meta-Learning using Submodular Mutual Information
Changbin Li, Suraj Kothawade, Feng Chen +1
Few-shot classification (FSC) requires training models using a few (typically one to five) data points per class. Meta learning has proven to be able to learn a parametrized model…