AIConfPaper
← Search

Rishabh Iyer

17 accepted papers

2023

DITTO: Data-efficient and Fair Targeted Subset Selection for ASR Accent Adaptation

Suraj Kothawade, Anmol Mekala, D.Chandra Sekhara Hetha Havya, Mayank Kothyari, Rishabh Iyer, Ganesh Ramakrishnan +1
ACL 2023long

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 target accent, a commonly adopted solution is to finetune the ASR model using accent-specific labeled speech. However, acquiring larg…

Cited by 8Source ↗PDF ↗Scholar ↗
2022

A Nested Bi-level Optimization Framework for Robust Few Shot Learning

Krishnateja Killamsetty, Changbin Li, Chen Zhao, Feng Chen, Rishabh Iyer
AAAI 2022technical

Model-Agnostic Meta-Learning (MAML), a popular gradient-based meta-learning framework, assumes that the contribution of each task or instance to the meta-learner is equal.Hence, it fails to address the domain shift between base and novel classes in few-shot learning. In this work, we propose a novel…

Cited by 16Source ↗PDF ↗code ↗Scholar ↗
2022

GCR: Gradient Coreset Based Replay Buffer Selection for Continual Learning

Rishabh Tiwari, Krishnateja Killamsetty, Rishabh Iyer, Pradeep Shenoy
CVPR 2022poster

Continual learning (CL) aims to develop techniques by which a single model adapts to an increasing number of tasks encountered sequentially, thereby potentially leveraging learnings across tasks in a resource-efficient manner. A major challenge for CL systems is catastrophic forgetting, where earlie…

Cited by 157PDF ↗Scholar ↗
2022

Learning to Robustly Aggregate Labeling Functions for Semi-supervised Data Programming

Ayush Maheshwari, Krishnateja Killamsetty, Ganesh Ramakrishnan, Rishabh Iyer, Marina Danilevsky, Lucian Popa
ACL 2022findings

A critical bottleneck in supervised machine learning is the need for large amounts of labeled data which is expensive and time-consuming to obtain. Although a small amount of labeled data cannot be used to train a model, it can be used effectively for the generation of humaninterpretable labeling fu…

Cited by 18Source ↗PDF ↗code ↗Scholar ↗
2022

PLATINUM: Semi-Supervised Model Agnostic Meta-Learning using Submodular Mutual Information

Changbin Li, Suraj Kothawade, Feng Chen, Rishabh Iyer
ICML 2022spotlight

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 for FSC by training on various other classification tasks. In this work, we propose PLATINUM (semi-suPervised modeL Agno…

Cited by 9Source ↗PDF ↗code ↗Scholar ↗
2022

PRISM: A Rich Class of Parameterized Submodular Information Measures for Guided Data Subset Selection

Suraj Kothawade, Vishal Kaushal, Ganesh Ramakrishnan, Jeff Bilmes, Rishabh Iyer
AAAI 2022technical

With ever-increasing dataset sizes, subset selection techniques are becoming increasingly important for a plethora of tasks. It is often necessary to guide the subset selection to achieve certain desiderata, which includes focusing or targeting certain data points, while avoiding others. Examples of…

Cited by 47Source ↗PDF ↗code ↗Scholar ↗
2022

Partitioned Gradient Matching-based Data Subset Selection for Compute-Efficient Robust ASR Training

Ashish Mittal, Durga Sivasubramanian, Rishabh Iyer, Preethi Jyothi, Ganesh Ramakrishnan
EMNLP 2022finding

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 problem if the subset selected could achieve on-par performance with training with the entire dataset. Although there are many…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2022

TALISMAN: Targeted Active Learning for Object Detection with Rare Classes and Slices Using Submodular Mutual Information

Suraj Kothawade, Saikat Ghosh, Sumit Shekhar, Yu Xiang, Rishabh Iyer
ECCV 2022poster

"Deep neural networks based object detectors have shown great success in a variety of domains like autonomous vehicles, biomedical imaging, etc. It is known that their success depends on a large amount of data from the domain of interest. While deep models often perform well in terms of overall accu…

Cited by 43Source ↗PDF ↗code ↗Scholar ↗
2021

GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learning

Krishnateja Killamsetty, Durga Sivasubramanian, Ganesh Ramakrishnan, Rishabh Iyer
AAAI 2021technical

Large scale machine learning and deep models are extremely data-hungry. Unfortunately, obtaining large amounts of labeled data is expensive, and training state-of-the-art models (with hyperparameter tuning) requires significant computing resources and time. Secondly, real-world data is noisy and imb…

Cited by 247Source ↗PDF ↗code ↗Scholar ↗
2021

GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training

Krishnateja Killamsetty, Durga S, Ganesh Ramakrishnan, Abir De, Rishabh Iyer
ICML 2021spotlight

The great success of modern machine learning models on large datasets is contingent on extensive computational resources with high financial and environmental costs. One way to address this is by extracting subsets that generalize on par with the full data. In this work, we propose a general framewo…

Cited by 267Source ↗PDF ↗code ↗Scholar ↗
2021

Training Data Subset Selection for Regression with Controlled Generalization Error

Durga S, Rishabh Iyer, Ganesh Ramakrishnan, Abir De
ICML 2021spotlight

Data subset selection from a large number of training instances has been a successful approach toward efficient and cost-effective machine learning. However, models trained on a smaller subset may show poor generalization ability. In this paper, our goal is to design an algorithm for selecting a sub…

Cited by 30Source ↗PDF ↗code ↗Scholar ↗
2019

A Memoization Framework for Scaling Submodular Optimization to Large Scale Problems

Rishabh Iyer, Jeffrey Bilmes
AISTATS 2019poster

We are motivated by large scale submodular optimization problems, where standard algorithms, which treat the submodular functions in the value oracle model, do not scale. In this paper, we present a new model called the pre-computational complexity model, along with a unifying memoization based fram…

Cited by 17Source ↗PDF ↗Scholar ↗
2019

Near Optimal Algorithms for Hard Submodular Programs with Discounted Cooperative Costs

Rishabh Iyer, Jeffrey Bilmes
AISTATS 2019poster

In this paper, we investigate a class of submodular problems which in general are very hard. These include minimizing a submodular cost function under combinatorial constraints, which include cuts, matchings, paths, etc., optimizing a submodular function under submodular cover and submodular knapsac…

Cited by 11Source ↗PDF ↗Scholar ↗
2015

On Approximate Non-submodular Minimization via Tree-Structured Supermodularity

Yoshinobu Kawahara, Rishabh Iyer, Jeffrey Bilmes
AISTATS 2015poster

We address the problem of minimizing non-submodular functions where the supermodularity is restricted to tree-structured pairwise terms. We are motivated by several real world applications, which require submodularity along with structured supermodularity, and this forms a rich class of expressive m…

Cited by 5Source ↗PDF ↗Scholar ↗