303 citations · 960 across the 44 of their papers we have counts for
18 papers · 1 filter
A data-centric weak supervised learning for highway traffic incident detection
Yixuan Sun, Tanwi Mallick, Prasanna Balaprakash +1
Using the data from loop detector sensors for near-real-time detection of traffic incidents in highways is crucial to averting major traffic congestion. While recent supervised mac…
AutoDEUQ: Automated Deep Ensemble with Uncertainty Quantification
Romain Egele, Romit Maulik, Krishnan Raghavan +3
Deep neural networks are powerful predictors for a variety of tasks. However, they do not capture uncertainty directly. Using neural network ensembles to quantify uncertainty is co…
Formalizing the Generalization-Forgetting Trade-off in Continual Learning
Krishnan Raghavan, Prasanna Balaprakash
We formulate the continual learning (CL) problem via dynamic programming and model the trade-off between catastrophic forgetting and generalization as a two-player sequential game.…
Autotuning PolyBench Benchmarks with LLVM Clang/Polly Loop Optimization Pragmas Using Bayesian Optimization (extended version)
Xingfu Wu, Michael Kruse, Prasanna Balaprakash +4
In this paper, we develop a ytopt autotuning framework that leverages Bayesian optimization to explore the parameter space search and compare four different supervised learning met…
AgEBO-Tabular: Joint Neural Architecture and Hyperparameter Search with Autotuned Data-Parallel Training for Tabular Data
Romain Egele, Prasanna Balaprakash, Venkatram Vishwanath +2
Developing high-performing predictive models for large tabular data sets is a challenging task. The state-of-the-art methods are based on expert-developed model ensembles from diff…
Dynamic Graph Neural Network for Traffic Forecasting in Wide Area Networks
Tanwi Mallick, Mariam Kiran, Bashir Mohammed +1
Wide area networking infrastructures (WANs), particularly science and research WANs, are the backbone for moving large volumes of scientific data between experimental facilities an…
Graph Neural Network Architecture Search for Molecular Property Prediction
Shengli Jiang, Prasanna Balaprakash
Predicting the properties of a molecule from its structure is a challenging task. Recently, deep learning methods have improved the state of the art for this task because of their…
Meta Continual Learning via Dynamic Programming
R. Krishnan, Prasanna Balaprakash
Meta continual learning algorithms seek to train a model when faced with similar tasks observed in a sequential manner. Despite promising methodological advancements, there is a la…
Neuromodulated Neural Architectures with Local Error Signals for Memory-Constrained Online Continual Learning
Sandeep Madireddy, Angel Yanguas-Gil, Prasanna Balaprakash
The ability to learn continuously from an incoming data stream without catastrophic forgetting is critical for designing intelligent systems. Many existing approaches to continual…
A Gradient-Aware Search Algorithm for Constrained Markov Decision Processes
Sami Khairy, Prasanna Balaprakash, Lin X. Cai
The canonical solution methodology for finite constrained Markov decision processes (CMDPs), where the objective is to maximize the expected infinite-horizon discounted rewards sub…
Transfer Learning with Graph Neural Networks for Short-Term Highway Traffic Forecasting
Tanwi Mallick, Prasanna Balaprakash, Eric Rask +1
Highway traffic modeling and forecasting approaches are critical for intelligent transportation systems. Recently, deep-learning-based traffic forecasting methods have emerged as s…
Learning to Optimize Variational Quantum Circuits to Solve Combinatorial Problems
Sami Khairy, Ruslan Shaydulin, Lukasz Cincio +2
Quantum computing is a computational paradigm with the potential to outperform classical methods for a variety of problems. Proposed recently, the Quantum Approximate Optimization…
Reinforcement-Learning-Based Variational Quantum Circuits Optimization for Combinatorial Problems
Sami Khairy, Ruslan Shaydulin, Lukasz Cincio +2
Quantum computing exploits basic quantum phenomena such as state superposition and entanglement to perform computations. The Quantum Approximate Optimization Algorithm (QAOA) is ar…
Using recurrent neural networks for nonlinear component computation in advection-dominated reduced-order models
Romit Maulik, Vishwas Rao, Sandeep Madireddy +2
Rapid simulations of advection-dominated problems are vital for multiple engineering and geophysical applications. In this paper, we present a long short-term memory neural network…
MaLTESE: Large-Scale Simulation-Driven Machine Learning for Transient Driving Cycles
Shashi M. Aithal, Prasanna Balaprakash
Optimal engine operation during a transient driving cycle is the key to achieving greater fuel economy, engine efficiency, and reduced emissions. In order to achieve continuously o…
Graph-Partitioning-Based Diffusion Convolutional Recurrent Neural Network for Large-Scale Traffic Forecasting
Tanwi Mallick, Prasanna Balaprakash, Eric Rask +1
Traffic forecasting approaches are critical to developing adaptive strategies for mobility. Traffic patterns have complex spatial and temporal dependencies that make accurate forec…
Scalable Reinforcement-Learning-Based Neural Architecture Search for Cancer Deep Learning Research
Prasanna Balaprakash, Romain Egele, Misha Salim +5
Cancer is a complex disease, the understanding and treatment of which are being aided through increases in the volume of collected data and in the scale of deployed computing power…
Neuromorphic Architecture Optimization for Task-Specific Dynamic Learning
Sandeep Madireddy, Angel Yanguas-Gil, Prasanna Balaprakash
The ability to learn and adapt in real time is a central feature of biological systems. Neuromorphic architectures demonstrating such versatility can greatly enhance our ability to…