136 citations · 293 across the 18 of their papers we have counts for
21 papers
Regularization Through Reasoning: Systematic Improvements in Language Model Classification via Explanation-Enhanced Fine-Tuning
Vivswan Shah, Randy Cogill, Hanwei Yue +2
Fine-tuning LLMs for classification typically maps inputs directly to labels. We ask whether attaching brief explanations to each label during fine-tuning yields better models. We…
Federated Representation Learning for Automatic Speech Recognition
Guruprasad V Ramesh, Gopinath Chennupati, Milind Rao +3
Federated Learning (FL) is a privacy-preserving paradigm, allowing edge devices to learn collaboratively without sharing data. Edge devices like Alexa and Siri are prospective sour…
Federated Self-Learning with Weak Supervision for Speech Recognition
Milind Rao, Gopinath Chennupati, Gautam Tiwari +4
Automatic speech recognition (ASR) models with low-footprint are increasingly being deployed on edge devices for conversational agents, which enhances privacy. We study the problem…
Learning When to Trust Which Teacher for Weakly Supervised ASR
Aakriti Agrawal, Milind Rao, Anit Kumar Sahu +2
Automatic speech recognition (ASR) training can utilize multiple experts as teacher models, each trained on a specific domain or accent. Teacher models may be opaque in nature sinc…
Can Calibration Improve Sample Prioritization?
Ganesh Tata, Gautham Krishna Gudur, Gopinath Chennupati +1
Calibration can reduce overconfident predictions of deep neural networks, but can calibration also accelerate training? In this paper, we show that it can when used to prioritize s…
ILASR: Privacy-Preserving Incremental Learning for Automatic Speech Recognition at Production Scale
Gopinath Chennupati, Milind Rao, Gurpreet Chadha +11
Incremental learning is one paradigm to enable model building and updating at scale with streaming data. For end-to-end automatic speech recognition (ASR) tasks, the absence of hum…
BB-ML: Basic Block Performance Prediction using Machine Learning Techniques
Hamdy Abdelkhalik, Shamminuj Aktar, Yehia Arafa +8
Recent years have seen the adoption of Machine Learning (ML) techniques to predict the performance of large-scale applications, mostly at a coarse level. In contrast, we propose to…
An Effective Baseline for Robustness to Distributional Shift
Sunil Thulasidasan, Sushil Thapa, Sayera Dhaubhadel +3
Refraining from confidently predicting when faced with categories of inputs different from those seen during training is an important requirement for the safe deployment of deep le…
PPT-Multicore: Performance Prediction of OpenMP applications using Reuse Profiles and Analytical Modeling
Atanu Barai, Yehia Arafa, Abdel-Hameed Badawy +3
We present PPT-Multicore, an analytical model embedded in the Performance Prediction Toolkit (PPT) to predict parallel application performance running on a multicore processor. PPT…
PPT-SASMM: Scalable Analytical Shared Memory Model: Predicting the Performance of Multicore Caches from a Single-Threaded Execution Trace
Atanu Barai, Gopinath Chennupati, Nandakishore Santhi +3
Performance modeling of parallel applications on multicore processors remains a challenge in computational co-design due to multicore processors' complex design. Multicores include…
Machine Learning Enabled Scalable Performance Prediction of Scientific Codes
Gopinath Chennupati, Nandakishore Santhi, Phill Romero +1
We present the Analytical Memory Model with Pipelines (AMMP) of the Performance Prediction Toolkit (PPT). PPT-AMMP takes high-level source code and hardware architecture parameters…
Decoy Selection for Protein Structure Prediction Via Extreme Gradient Boosting and Ranking
Nasrin Akhter, Gopinath Chennupati, Hristo Djidjev +1
Identifying one or more biologically-active/native decoys from millions of non-native decoys is one of the major challenges in computational structural biology. The extreme lack of…
Why I'm not Answering: Understanding Determinants of Classification of an Abstaining Classifier for Cancer Pathology Reports
Sayera Dhaubhadel, Jamaludin Mohd-Yusof, Kumkum Ganguly +13
Safe deployment of deep learning systems in critical real world applications requires models to make very few mistakes, and only under predictable circumstances. In this work, we a…
Distributed Non-Negative Tensor Train Decomposition
Manish Bhattarai, Gopinath Chennupati, Erik Skau +3
The era of exascale computing opens new venues for innovations and discoveries in many scientific, engineering, and commercial fields. However, with the exaflops also come the extr…
Verified Instruction-Level Energy Consumption Measurement for NVIDIA GPUs
Yehia Arafa, Ammar ElWazir, Abdelrahman ElKanishy +6
GPUs are prevalent in modern computing systems at all scales. They consume a significant fraction of the energy in these systems. However, vendors do not publish the actual cost of…
Modeling Shared Cache Performance of OpenMP Programs using Reuse Distance
Atanu Barai, Gopinath Chennupati, Nandakishore Santhi +2
Performance modeling of parallel applications on multicore computers remains a challenge in computational co-design due to the complex design of multicore processors including priv…
On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks
Sunil Thulasidasan, Gopinath Chennupati, Jeff Bilmes +2
Mixup~\cite{zhang2017mixup} is a recently proposed method for training deep neural networks where additional samples are generated during training by convexly combining random pair…
Combating Label Noise in Deep Learning Using Abstention
Sunil Thulasidasan, Tanmoy Bhattacharya, Jeff Bilmes +2
We introduce a novel method to combat label noise when training deep neural networks for classification. We propose a loss function that permits abstention during training thereby…
Low Overhead Instruction Latency Characterization for NVIDIA GPGPUs
Yehia Arafa, Abdel-Hameed Badawy, Gopinath Chennupati +2
The last decade has seen a shift in the computer systems industry where heterogeneous computing has become prevalent. Graphics Processing Units (GPUs) are now present in supercompu…
Quantum Algorithm Implementations for Beginners
Abhijith J., Adetokunbo Adedoyin, John Ambrosiano +31
As quantum computers become available to the general public, the need has arisen to train a cohort of quantum programmers, many of whom have been developing classical computer prog…
eAnt-Miner : An Ensemble Ant-Miner to Improve the ACO Classification
Gopinath Chennupati
Ant Colony Optimization (ACO) has been applied in supervised learning in order to induce classification rules as well as decision trees, named Ant-Miners. Although these are compet…