217 citations · 259 across the 16 of their papers we have counts for
18 papers
Automatic Task Parallelization of Dataflow Graphs in ML/DL models
Srinjoy Das, Lawrence Rauchwerger
Several methods exist today to accelerate Machine Learning(ML) or Deep-Learning(DL) model performance for training and inference. However, modern techniques that rely on various gr…
Model-Based and Model-Free point prediction algorithms for locally stationary random fields
Srinjoy Das, Yiwen Zhang, Dimitris N. Politis
The Model-free Prediction Principle has been successfully applied to general regression problems, as well as problems involving stationary and locally stationary time series. In th…
Effective City Planning: A Data Driven Analysis of Infrastructure and Citizen Feedback in Bangalore
Srishti Mishra, Srinjoy Das
Leveraging civic data, divided into 3 categories spending, infrastructure and citizen feedback, can present a clear picture of the priorities, performance, and pain-points of a cit…
Training Deep Neural Networks with Joint Quantization and Pruning of Weights and Activations
Xinyu Zhang, Ian Colbert, Ken Kreutz-Delgado +1
Quantization and pruning are core techniques used to reduce the inference costs of deep neural networks. State-of-the-art quantization techniques are currently applied to both the…
Tuning Confidence Bound for Stochastic Bandits with Bandit Distance
Xinyu Zhang, Srinjoy Das, Ken Kreutz-Delgado
We propose a novel modification of the standard upper confidence bound (UCB) method for the stochastic multi-armed bandit (MAB) problem which tunes the confidence bound of a given…
Kernel distance measures for time series, random fields and other structured data
Srinjoy Das, Hrushikesh Mhaskar, Alexander Cloninger
This paper introduces kdiff, a novel kernel-based measure for estimating distances between instances of time series, random fields and other forms of structured data. This measure…