Publications
Open-source software
Posters
Talks

Publications

See Google Scholar for an up-to-date list of publications.

Open-source software

[1]	P. Balaprakash, R. Egele, M. Salim, V. Vishwanath, and S. M. Wild. DeepHyper: Scalable Asynchronous Neural Architecture and Hyperparameter Search for Deep Neural Networks, 2018. DeepHyper: Scalable automated machine learning package with two components: 1) Reinforcement-learning-based neural architecture search for automatically constructing high-performing the deep neural network architecture; 2) Asynchronous model-based search for finding high-performing hyperparameters for deep neural networks. [ bib | http ]
[2]	P. Agarwal, P. Balaprakash, S. Leyffer, and S. M. Wild. SPUDS: Smart Pipeline for Urban Data Science, 2017. SPUDS is a machine-learning pipeline to build classification models to rank food establishments that are at most risk for the types of violations most likely to spread food-borne illness. The pipeline balances the the training data with resampling techniques, identifies the most important factors leading to critical violations via variable importance and variable selection methods, evaluates several state-of-the-art learning with cross validation, and finally combines the best performing ones via bagging. It is a customized version of AutoMOMML, exclusively designed for City of Chicago Smart Data Platform, and implemented in Python. [ bib | http ]
[3]	P. Balaprakash, A. Tiwari, S. M. Wild, L. Carrington, and P. D. Hovland. AutoMOMML: Automatic Multi-objective Modeling with Machine Learning, 2016. AutoMOMML is an end-to-end, machine-learning-based framework to build predictive models for objectives such as performance, and power. The framework adopts statistical approaches to reduce the modeling complexity and automatically identifies and configures the most suitable learning algorithm to model the required objectives based on hardware and application signatures. [ bib | http ]
[4]	P. Balaprakash, A. Mametjanov, C. Choudary, P. D. Hovland, S. M. Wild, and G. Sabin. FPGAtuner: Autotuning FPGA Design Parameters for Performance and Power, 2016. A machine-learning-based approach to tune FPGA design parameters. It performs sampling-based reduction of the parameter space and guides the search toward promising parameter configurations. [ bib | http ]
[5]	P. Balaprakash. SuRF: Search using Random Forest, 2015. SuRF is a model-based search module for automatic performance tuning. It adopts random forest supervised learning algorithm for modeling the performances as a function of input parameters within the search. SuRF samples a small number of parameter configurations, empirically evaluating the corresponding code variants to obtain the corresponding performance metrics, and fitting a surrogate model over the input-output space. The surrogate model is then iteratively refined by obtaining new output metrics at unevaluated input configurations predicted to be high-performing by the model. Implemented in Python and available with the Orio autotuning framework. [ bib | http ]
[6]	P. Balaprakash, S. M. Wild, and B. Norris. SPAPT: Search Problems in Automatic Performance Tuning, 2011. A set of extensible and portable search problems in automatic performance tuning whose goal is to aid in the development and improvement of search strategies and performance-improving transformations. SPAPT contains representative implementations from a number of lower-level, serial performance-tuning tasks in scientific applications. Available with the Orio autotuning framework. [ bib | http ]
[7]	M. L. Ibanez, J. D. Lacoste, T. Stützle, M. Birattari, E. Yuan, and P. Balaprakash. The irace Package: Iterated Race for Automatic Algorithm Configuration, 2010. The irace package implements the iterated racing procedure, which is an extension of the Iterated F-race procedure. Its main purpose is to automatically configure optimization algorithms by finding the most appropriate settings given a set of instances of an optimization problem. It builds upon the race package by Birattari, and it is implemented in R. [ bib | http ]
[8]	P. Balaprakash, M. Birattari, and T. Stützle. ELS-PTSP: Estimation-based Local Search for the Probabilistic Traveling Salesman Problem, 2009. This software package provides a high-performance implementation of the estimation-based iterative improvement algorithm to tackle the probabilistic traveling salesman problem. A key novelty of the proposed algorithm is that the cost difference between two neighbor solutions is estimated by partial evaluation, adaptive, and importance sampling. Developed in C with GNU scientific library under Linux. [ bib | http ]

Talks and poster presentations

[1]	P. Balaprakash. Ytopt/SuRF: Machine-Learning-Based Search for Autotuning. 2021 ECP Annual Meeting, April 2021. [ bib ]
[2]	P. Balaprakash. In situ compression artifact removal in scientific data using deep transfer learning and experience replay. Impacts of Applied Mathematics and Computer Science on DOE Computational Science, SIAM Conference on Computational Science and Engineering, March 2021. [ bib ]
[3]	P. Balaprakash. Scientific domain-informed machine learning. Sustainable Horizon Institute, March 2021. [ bib ]
[4]	P. Balaprakash. DeepHyper: A Hyperparameter Search Package for Deep Neural Networks. ALCF Simulation, Data, and Learning Workshop, Argonne, IL, December 2020. [ bib ]
[5]	P. Balaprakash. Enabling ml approaches to hpc systems operations. Panel, IEEE Cluster Workshop on Monitoring and Analsis for High Performance Computing Sytems Plus Applications (HPCMASPA), September 2020. [ bib ]
[6]	P. Balaprakash. Automated machine learning for molecular chemistry. Artificial Intelligence for Water Workshop, Argonne, IL, September 2020. [ bib ]
[7]	P. Balaprakash. DeepHyper and hyperparameter optimization. ATPESC 2020: Argonne Training Program on Extreme-Scale Computing, August 2020. [ bib ]
[8]	P. Balaprakash. Machine-learning-based automatic performance tuning. Workshop on Program Synthesis for Scientific Computing, August 2020. [ bib ]
[9]	P. Balaprakash. DeepHyper: Scalable Automated Machine Learning Package. Argonne CPS Division seminar series, August 2020. [ bib ]
[10]	P. Balaprakash. Keynote – the future of hpc systems in the presence of ai. Panel, Smoky Mountains Computational Sciences and Engineering Conference (SMC), August 2020. [ bib ]
[11]	P. Balaprakash. DeepHyper: A Hyperparameter Search Package for Deep Neural Networks. ALCF Computational Performance Workshop, Argonne, IL, May 2020. [ bib ]
[12]	P. Balaprakash. Artificial intelligence and machine learning. AI for Sustainability Workshop, April 2020. [ bib ]
[13]	P. Balaprakash. Reinforcement learning and applications. SciDAC TDS Meeting, March 2020. [ bib ]
[14]	P. Balaprakash. Neuromorphic acceleration for uncertainty quantification in deep neural networks. MCS All Hands Meeting, Argonne, IL, January 2020. [ bib ]
[15]	P. Balaprakash. Artificial intelligence for science. TRB ExComm A.I. Policy Session, January 2020. [ bib ]
[16]	P. Balaprakash. Scalable reinforcement-learning-based neural architecture search for cancer research. SC '19: IEEE/ACM International Conference on High Performance Computing, Networking, Storage and Analysis, November 2019. [ bib ]
[17]	P. Balaprakash. DeepHyper: A Hyperparameter Search Package for Deep Neural Networks. ALCF Simulation, Data, and Learning Workshop, Argonne, IL, October 2019. [ bib ]
[18]	P. Balaprakash. DeepHyper: A Hyperparameter Search Package for Deep Neural Networks. ALCF Developer Session, September 2019. [ bib ]
[19]	P. Balaprakash. AI tools. PSE AI in Science and Engineering Workshop, Argonne, IL, September 2019. [ bib ]
[20]	P. Balaprakash. Hyperparameter optimization and DeepHyper. ATPESC 2019: Argonne Training Program on Extreme-Scale Computing, St. Charles, IL, August 2019. [ bib ]
[21]	P. Balaprakash. Recurrent networks for time series data. Argonne Artificial Intelligence for Science Workshop, Argonne, IL, August 2019. [ bib ]
[22]	P. Balaprakash. Deep learning basics. Artificial Intelligence for Science Workshop, Argonne, IL, August 2019. [ bib ]
[23]	P. Balaprakash. Deep learning basics. ATPESC 2019: Argonne Training Program on Extreme-Scale Computing, St. Charles, IL, August 2019. [ bib ]
[24]	P. Balaprakash. Deep learning basics. Artificial Intelligence for Science Workshop for Summer Students, Argonne, IL, July 2019. [ bib ]
[25]	P. Balaprakash. Recurrent networks for time series data. Artificial Intelligence for Science Workshop for Summer Students, Argonne, IL, July 2019. [ bib ]
[26]	P. Balaprakash. Scientific domain-informed machine learning. Argonne Physics Divison Colloquium, Argonne, IL, May 2019. [ bib ]
[27]	P. Balaprakash. Artificial intelligence to accelerate discovery and development. Argonne Outloud Public Lecture, Argonne, IL, May 2019. [ bib ]
[28]	P. Balaprakash. DeepHyper: Scalable Asynchronous Hyperparameter Search for Deep Learning. Data Enabled Modeling and Discovery in Science and Engineering Minisymposium, SIAM Conference on Computational Science and Engineering, February 2019. [ bib ]
[29]	P. Balaprakash. Machine-learning-based-search for automatic performance tuning. OMASE 2019: Optimization, Modeling, Analysis and Space Exploration Workshop, Washington DC, February 2019. [ bib ]
[30]	P. Balaprakash. Machine-learning-based performance modeling and tuning for high-performance computing. HPCaML 2019: The First International Workshop on the Intersection of High Performance Computing and Machine Learning, Washington DC, February 2019. [ bib ]
[31]	P. Balaprakash. Scalable reinforcement-learning-based neural architecture search for scientific and engineering applications. LANS Informal Seminar, Argonne, IL, February 2019. [ bib ]
[32]	P. Balaprakash. Evaluating deep neural network to spiking neural networks transformation for DOE scientific applications on Intel Loihi. 2019 LDRD Expedition, Argonne, IL, 2019. [ bib ]
[33]	P. Balaprakash. Scientific domain-informed machine learning. Advanced Photon Source Colloquium, Argonne, IL, December 2018. [ bib ]
[34]	P. Balaprakash. Scientific domain-informed machine learning. Indian Institute of Science, Bengaluru, India, December 2018. [ bib ]
[35]	P. Balaprakash. DeepHyper: Asynchronous Hyperparameter Search for Deep Neural Networks. 25th IEEE International Conference on High Performance Computing, Data, and Analytics, Bengaluru, India, December 2018. [ bib ]
[36]	P. Balaprakash. Scientific domain-informed machine learning. Consortium for Computational Physics and Chemistry Meeting, Argonne, IL, November 2018. [ bib ]
[37]	P. Balaprakash. Spatial-temporal deep learning and hyperparameter search for traffic prediction. Workshop on Large-Scale Computing for Transportation Studies, Maui, HI, November 2018. [ bib ]
[38]	P. Balaprakash. Benchmarking machine learning methods for performance modeling of scientific applications. PMBS 2018: Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems, November 2018. [ bib ]
[39]	P. Balaprakash. Scientific domain-informed machine learning. ALCF Simulation, Data, and Learning Workshop, Argonne, IL, October 2018. [ bib ]
[40]	P. Balaprakash. Reproducibility, portability and interpretability of deep learning. Workshop on Deep Learning for Multimessenger Astrophysics: Real-time Discovery at Scale, October 2018. [ bib ]
[41]	P. Balaprakash. Scientific domain-informed machine learning. Department Seminar Series, Mechanical and Industrial Engineering, University of Illinois at Chicago, IL, October 2018. [ bib ]
[42]	P. Balaprakash. Data parallel deep learning. CANDLE-EXALEARN ECP Workshop, Argonne, IL, October 2018. [ bib ]
[43]	P. Balaprakash. Data for machine learning. Argonne Geospatial Workshop, August 2018. [ bib ]
[44]	P. Balaprakash. Machine learning hardware. SciDAC Fusion Machine-Learning Workshop 2018, Princeton, NJ, June 2018. [ bib ]
[45]	P. Balaprakash. Tools for scientific machine learning. Army Research Lab Workshop, Chicago, IL, May 2018. [ bib ]
[46]	P. Balaprakash. Machine learning overview and applications. Argonne Environmental Science Division Retreat, May 2018. [ bib ]
[47]	P. Balaprakash. Machine learning in high performance computing. 7th Greater Chicago Area Systems Research Workshop University of Chicago, Chicago, IL, April 2018. [ bib ]
[48]	P. Balaprakash. Neuromorphic Acceleration for Approximate Bayesian Inference on Neural Networks via Permanent Dropout. 2018 LDRD Expedition, Argonne, IL, 2018. [ bib ]
[49]	P. Balaprakash. Recurrent neural networks. Argonne Deep Learning Workshop, January 2018. [ bib ]
[50]	P. Balaprakash. Deep learning basics. Argonne Deep Learning Workshop, January 2018. [ bib ]
[51]	P. Balaprakash. Introduction to unsupervised and supervised learning in python: Hands-on tutorial. Argonne Training Program on Extreme-Scale Computing (ATPESC), St. Charles, IL, August 2017. [ bib ]
[52]	P. Balaprakash. Overview of machine learning methods. Argonne Training Program on Extreme-Scale Computing (ATPESC), St. Charles, IL, August 2017. [ bib ]
[53]	P. Balaprakash. Need for data locality in machine/deep learning. Fourth Workshop on Programming Abstractions for Data Locality (PADAL'17), Chicago, IL, August 2017. [ bib ]
[54]	P. Balaprakash. Automatic multi-objective modeling with machine learning. Argonne Training Program on Extreme-Scale Computing (ATPESC), St. Charles, IL, August 2017. [ bib ]
[55]	P. Balaprakash. Overview of machine learning methods. Argonne Machine Learning Workshop, Argonne, IL, July 2017. [ bib ]
[56]	P. Balaprakash. Generative adversarial networks. US ATLAS Workshop, Argonne, IL, July 2017. [ bib ]
[57]	P. Balaprakash. Introduction to unsupervised and supervised learning in python: Hands-on tutorial. Argonne Machine Learning Workshop, Argonne, IL, July 2017. [ bib ]
[58]	P. Balaprakash. Automatic multi-objective modeling with machine learning. Argonne Machine Learning Workshop, Argonne, IL, July 2017. [ bib ]
[59]	P. Balaprakash. Generative adversarial networks. The 3rd International Workshop on Data Science in High Energy Physics (DS@HEP 2017), Fermi National Accelerator Laboratory, IL, May 2017. [ bib ]
[60]	P. Balaprakash. Automatic multi-objective modeling with machine learning. Workshop on Optimization and Machine Learning (ACNTW 17), Northwestern University, Argonne, May 2017. [ bib ]
[61]	P. Balaprakash. Analytical performance modeling and validation of intel's xeon phi architecture. Computing Frontiers 2017, University of Siena, Siena, Italy, May 2017. [ bib ]
[62]	P. Balaprakash. Artificial intelligence for transportation and mobility. Tech Hub, SAE World Congress 2017, Detroit, MI, May 2017. [ bib ]
[63]	P. Balaprakash. Introduction to unsupervised and supervised learning in python: Hands-on tutorial. Argonne Machine Learning Workshop, Argonne, IL, April 2017. [ bib ]
[64]	P. Balaprakash. Automatic multi-objective modeling with machine learning. Argonne Machine Learning Workshop, Argonne, IL, April 2017. [ bib ]
[65]	P. Balaprakash. Overview of machine learning methods. Argonne Machine Learning Workshop, Argonne, IL, April 2017. [ bib ]
[66]	P. Balaprakash. Machine learning for high performance computing. Midwest Big Data Opportunities and Challenges, Chicago, IL, September 2016. [ bib ]
[67]	P. Balaprakash. Improving data transfer throughput with direct search optimization. The 45th International Conference on Parallel Processing, ICPP 2016, Philadelphia, PA, August 2016. [ bib ]
[68]	P. Balaprakash. AutoMOMML: Automatic Multi-Objective Modeling with Machine Learning. Argonne Leadership Computing Facility, Argonne, IL, June 2016. [ bib ]
[69]	P. Balaprakash. Multi objective optimization of HPC kernels for performance, power, and energy. 6th Joint Laboratory for Extreme Scale Computing (JLESC) Workshop, Kobe, Japan, June 2016. [ bib ]
[70]	P. Balaprakash. AutoMOMML: Automatic Multi-objective Modeling with Machine Learning. International Supercomputing Conference, ISC 2016, Frankfurt, Germany, June 2016. [ bib ]
[71]	P. Balaprakash. AutoMOMML: Automatic Multi-objective Modeling with Machine Learning. 5th Joint Laboratory for Extreme Scale Computing (JLESC) Workshop, Lyon, France, June 2016. [ bib ]
[72]	P. Balaprakash. Exploiting performance portability in search algorithms for autotuning. 11th International Workshop on Automatic Performance Tuning, iWAPT 2016, Chicago, IL, May 2016. [ bib ]
[73]	P. Balaprakash. Predictive modeling for large scale vehicle simulations. Urban Data Analytics/City of Chicago SmartData Platform Workshop, Chicago, IL, May 2015. [ bib ]
[74]	P. Balaprakash, V. Morozov, and R. Kettimuthu. Improving throughput by dynamically adapting concurrency of data transfer. High Performance Computing, Networking, Storage and Analysis (SCC), 2015 SC, 2015. Poster. [ bib ]
[75]	Y. Alexeev and P. Balaprakash. Heuristic dynamic load balancing algorithm applied to the fragment molecular orbital method. High Performance Computing, Networking, Storage and Analysis (SCC), 2015 SC, 2015. Poster. [ bib ]
[76]	P. Balaprakash. Self-aware runtime and operating systems. 2015 DOE ASCR Machine Learning Workshop, Rockville, MD, January 2015. [ bib ]
[77]	P. Balaprakash. Automatic performance modeling and tuning. Department of Mathematics, Statistics and Computer Science Colloquium, Marquette University, Milwaukee, WI, October 2014. [ bib ]
[78]	P. Balaprakash. Machine-learning-based load balancing for community ice code component in CESM. 11th International Meeting on High-Performance Computing for Computational Science (VECPAR 2014), Eugene, OR, July 2014. Conference Talk. [ bib ]
[79]	P. Balaprakash. Active-learning-based surrogate models for empirical performance tuning. Computation Institute, UChicago, Lemont, IL, February 2014. [ bib ]
[80]	Y. Zhang, P. Balaprakash, J. Meng, V. Morozov, S. Parker, and K. Kumaran. Raexplore: Enabling rapid, automated architecture exploration for full applications. High Performance Computing, Networking, Storage and Analysis (SCC), 2014 SC, 2014. Poster. [ bib ]
[81]	L. A. Gomez, P. Balaprakash, M.-S. Bouguerra, S. M. Wild, F. Cappello, and P. D. Hovland. Energy-performance tradeoffs in multilevel checkpoint strategies. 2014 IEEE International Conference on Cluster Computing (CLUSTER), 2014. Poster. [ bib ]
[82]	P. Balaprakash. Active-learning-based surrogate models for empirical performance tuning. 10th workshop of the INRIA-Illinois-ANL Joint Laboratory, Urbana, IL, November 2013. [ bib ]
[83]	P. Balaprakash. Multi objective optimization of HPC kernels for performance, power, and energy. 4th International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS13), Denver, CO, November 2013. [ bib ]
[84]	P. Balaprakash. Active-learning-based surrogate models for empirical performance tuning. 2013 IEEE International Conference on Cluster Computing (CLUSTER), Indianapolis, IN, September 2013. [ bib ]
[85]	P. Balaprakash. Search algorithms in empirical performance tuning and machine learning for computationally expensive simulations. PMaC/SDSC Seminar, San Diego, CA, July 2013. [ bib ]
[86]	P. Balaprakash, A. Tiwari, and S. M. Wild. Framework for optimizing power, energy, and performance. High Performance Computing, Networking, Storage and Analysis (SCC), 2013 SC, 2013. Poster. Finalist for the best poster award. [ bib ]
[87]	P. Balaprakash, D. Buntinas, A. Chan, A. Guha, R. Gupta, S. Narayanan, A. Chien, P. Hovland, and B. Norris. Exascale workload characterization and architecture implications. 2013 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), 2013. Poster. [ bib ]
[88]	P. Balaprakash. Search algorithms in empirical performance tuning and machine learning for computationally expensive simulations. ANL Mathematics and Computer Science Division Seminar, Lemont, IL, December 2012. [ bib ]
[89]	P. Balaprakash. A sequential learning approach for quantum chemistry simulations. IPAM Chemical Compound Space Reunion, Lake Arrowhead, CA, December 2012. [ bib ]
[90]	P. Balaprakash. SPAPT: Search Problems in Automatic Performance Tuning. Workshop on Tools for Program Development and Analysis in Computational Science, International Conference on Computational Science, ICCS 2012, Omaha, NE, June 2012. [ bib ]
[91]	P. Balaprakash. Active-learning-based surrogate models for empirical performance tuning. Computation Institute, Argonne, IL, February 2012. [ bib ]
[92]	P. Balaprakash. Search algorithms in empirical performance tuning and machine learning for computationally expensive simulations. LANS Informal Seminar, Argonne, IL, February 2012. [ bib ]
[93]	P. Balaprakash. Efficient optimization algorithms for empirical performance tuning. SIAM Conference on Parallel Processing (SIAM PP 2012), Savannah, GA, February 2012. [ bib ]
[94]	P. Balaprakash, D. Buntinas, A. Chan, A. Guha, R. Gupta, S. Narayanan, A. Chien, P. Hovland, and B. Norris. An exascale workload study. High Performance Computing, Networking, Storage and Analysis (SCC), 2012 SC Companion, 2012. Poster. [ bib ]
[95]	P. Balaprakash. Global and local search algorithms in empirical performance tuning. DOE CScADS Workshop on Libraries and Autotuning for Extreme-Scale Systems, Snowbird, UT, August 2011. [ bib ]
[96]	P. Balaprakash. Can search algorithms save large-scale automatic performance tuning? Workshop on Automatic Performance Tuning, International Conference on Computational Science, ICCS 2011, Singapore, June 2011. [ bib ]
[97]	P. Balaprakash. Comparison of search strategies in empirical performance tuning of linear algebra kernels. 2011 SIAM Conference on Computational Science and Engineering, Reno, NV, March 2011. [ bib ]
[98]	P. Balaprakash, S. M. Wild, and P. D. Hovland. Model-based optimization algorithms for empirical performance tuning. 2011 DOE Applied Mathematics Program Meeting, 2011. Poster. [ bib ]
[99]	P. Balaprakash. An experimental study of estimation-based metaheuristics for the probabilistic traveling salesman problem. LION 2007 II: Learning and Intelligent Optimization, Trento, Italy, December 2007. [ bib ]
[100]	P. Balaprakash. Improvement strategies for the F-Race algorithm: Sampling design and iterative refinement. 4th International Workshop on Hybrid Metaheuristics, Dortmund, Germany, October 2007. [ bib ]
[101]	P. Balaprakash. ACO/F-Race: Ant colony optimization and racing techniques for combinatorial optimization under uncertainty. MIC 2005: The 6th Metaheuristics International Conference, Vienna, Austria, August 2005. [ bib ]