Publications

2017

1. Deep Learning Inspired Prognostics Scheme for Applications Generating Big Data

   Krishnan Raghavan, Sarangapani Jagannathan, and V. A. Samaranayake

   In International Joint Conference on Neural Networks (AR:15), 2017

   Bib

   @inproceedings{raghavanDeepLearningInspired2017,
     title = {Deep Learning Inspired Prognostics Scheme for Applications Generating Big Data},
     booktitle = {International {{Joint Conference}} on {{Neural Networks}} ({{AR}}:15)},
     author = {Raghavan, Krishnan and Jagannathan, Sarangapani and Samaranayake, V. A.},
     year = {2017},
     pages = {3296--3302},
     publisher = {{IEEE}},
   }

2018

1. Distributed Learning of Deep Sparse Neural Networks for High-Dimensional Classification

   Shweta Garg, Krishnan Raghavan, Sarangapani Jagannathan, and 1 more author

   In IEEE International Conference on Big Data (AR:18.7), 2018

   Bib

   @inproceedings{gargDistributedLearningDeep2018a,
     title = {Distributed Learning of Deep Sparse Neural Networks for High-Dimensional Classification},
     booktitle = {{{IEEE International Conference}} on {{Big Data}} ({{AR}}:18.7)},
     author = {Garg, Shweta and Raghavan, Krishnan and Jagannathan, Sarangapani and Samaranayake, V. A.},
     year = {2018},
     pages = {1587--1592},
     publisher = {{IEEE}},
   }

2. A Multi-Step Nonlinear Dimension-Reduction Approach with Applications to Bigdata

   Krishnan Raghavan, V.A. Samaranayake, and S. Jagannathan

   In INNS Conference on Big Data and Deep Learning, 2018

   Abs Bib

   In this paper, a multi-step dimension-reduction approach is proposed for addressing nonlinear relationships within attributes. In this work, the attributes in the data are first organized into groups. In each group, the dimensions are reduced via a parametric mapping that takes into account nonlinear relationships. Mapping parameters are estimated using a low rank singular value decomposition (SVD) of distance covariance. Subsequently, the attributes are reorganized into groups based on the magnitude of their respective singular values. The group-wise organization and the subsequent reduction process is performed for multiple steps until a singular value-based user-defined criterion is satisfied. Simulation analysis is utilized to investigate the performance with five big data-sets.

   @inproceedings{KRISHNAN201881,
     title = {A Multi-Step Nonlinear Dimension-Reduction Approach with Applications to Bigdata},
     booktitle = {{{INNS}} Conference on {{Big Data}} and {{Deep Learning}}},
     author = {Raghavan, Krishnan and Samaranayake, V.A. and Jagannathan, S.},
     year = {2018},
     volume = {144},
     pages = {81--88},
     doi = {10.1016/j.procs.2018.10.507},
     url = {https://www.sciencedirect.com/science/article/pii/S1877050918322166},
   }

3. Direct Error Driven Learning for Deep Neural Networks with Applications to Bigdata

   Krishnan Raghavan, Sarangapani Jagannathan, and V. A. Samaranayake

   In International Conference on Big Data and Deep Learning, 2018

   Bib

   @inproceedings{raghavanDirectErrorDriven2018,
     title = {Direct Error Driven Learning for Deep Neural Networks with Applications to Bigdata},
     booktitle = {International {{Conference}} on {{Big Data}} and {{Deep Learning}}},
     author = {Raghavan, Krishnan and Jagannathan, Sarangapani and Samaranayake, V. A.},
     year = {2018},
     volume = {144},
     pages = {89--95},
     publisher = {{Elsevier}},
     url = {https://link.springer.com/chapter/10.1007/978-3-030-31764-5_1https://link.springer.com/chapter/10.1007/978-3-030-31764-5_1},
   }

4. A Minimax Approach for Classification with Big-data

   Krishnan Raghavan, Sarangapani Jagannathan, and V. A. Samaranayake

   In IEEE International Conference on Big Data (AR: 18.7), 2018

   Bib

   @inproceedings{raghavanMinimaxApproachClassification2018,
     title = {A {{Minimax Approach}} for {{Classification}} with {{Big-data}}},
     booktitle = {{{IEEE International Conference}} on {{Big Data}} ({{AR}}: 18.7)},
     author = {Raghavan, Krishnan and Jagannathan, Sarangapani and Samaranayake, V. A.},
     year = {2018},
     pages = {1437--1444},
     publisher = {{IEEE}},
   }

5. A Multi-Step Nonlinear Dimension-Reduction Approach with Applications to Big Data

   Krishnan Raghavan, V. A. Samaranayake, and Sarangapani Jagannathan

   2018

2019

1. Deep Neural Network Learning-Based Classifier Design for Big-Data Analytics

   Krishnan Raghavan

   2019

   Bib

   @thesis{raghavanDeepNeuralNetwork2019,
     title = {Deep Neural Network Learning-Based Classifier Design for Big-Data Analytics},
     author = {Raghavan, Krishnan},
     year = {2019},
     institution = {{Missouri University of Science and Technology}},
   }

2. Direct Error-Driven Learning for Deep Neural Networks with Applications to Big Data

   Krishnan Raghavan, Sarangapani Jagannathan, and V. A. Samaranayake

   2019

   Bib

   @article{raghavanDirectErrordrivenLearning2019,
     title = {Direct Error-Driven Learning for Deep Neural Networks with Applications to Big Data},
     author = {Raghavan, Krishnan and Jagannathan, Sarangapani and Samaranayake, V. A.},
     year = {2019},
     journaltitle = {IEEE Transactions on Neural Networks and Learning Systems (IF:11.623)},
     volume = {31},
     number = {5},
     pages = {1763--1770},
     publisher = {{IEEE}},
   }

3. A Hierarchical Dimension Reduction Approach for Big Data with Application to Fault Diagnostics

   Krishnan Raghavan, V. A. Samaranayake, and S. Jagannathan

   2019

   Bib

   @article{raghavanHierarchicalDimensionReduction2019,
     title = {A Hierarchical Dimension Reduction Approach for Big Data with Application to Fault Diagnostics},
     author = {Raghavan, Krishnan and Samaranayake, V. A. and Jagannathan, S.},
     year = {2019},
     journaltitle = {Big Data Research (IF: 3.739)},
     volume = {18},
     number = {0},
     pages = {100121},
     publisher = {{Elsevier}},
     url = {https://www.sciencedirect.com/science/article/pii/S2214579619302102},
   }

2020

1. Direct Error Driven Learning for Classification in Applications Generating Big-Data

   Krishnan Raghavan, S. Jagannathan, and V. A. Samaranayake

   In Development and Analysis of Deep Learning Architectures, 2020

   Bib

   @incollection{raghavanDirectErrorDriven2020,
     title = {Direct {{Error Driven Learning}} for {{Classification}} in {{Applications Generating Big-Data}}},
     booktitle = {Development and {{Analysis}} of {{Deep Learning Architectures}}},
     author = {Raghavan, Krishnan and Jagannathan, S. and Samaranayake, V. A.},
     year = {2020},
     pages = {1--29},
     publisher = {{Springer}},
     url = {https://www.sciencedirect.com/science/article/pii/S1877050918322178},
   }

2. Distributed Min–Max Learning Scheme for Neural Networks With Applications to High-Dimensional Classification

   Krishnan Raghavan, Shweta Garg, Sarangapani Jagannathan, and 1 more author

   2020

   Bib

   @article{raghavanDistributedMinMax2020,
     title = {Distributed {{Min}}–{{Max Learning Scheme}} for {{Neural Networks With Applications}} to {{High-Dimensional Classification}}},
     author = {Raghavan, Krishnan and Garg, Shweta and Jagannathan, Sarangapani and Samaranayake, V. A.},
     year = {2020},
     journaltitle = {IEEE transactions on neural networks and learning systems (IF:11.623)},
     volume = {32},
     number = {10},
     pages = {4323--4333},
     publisher = {{IEEE}},
   }

2021

1. Optimal Adaptive Control of Partially Uncertain Linear Continuous-Time Systems with State Delay

   Rohollah Moghadam, S. Jagannathan, Vignesh Narayanan, and 1 more author

   In Handbook of Reinforcement Learning and Control, 2021

   Bib

   @incollection{moghadamOptimalAdaptiveControl2021,
     title = {Optimal {{Adaptive Control}} of {{Partially Uncertain Linear Continuous-Time Systems}} with {{State Delay}}},
     booktitle = {Handbook of {{Reinforcement Learning}} and {{Control}}},
     author = {Moghadam, Rohollah and Jagannathan, S. and Narayanan, Vignesh and Raghavan, Krishnan},
     year = {2021},
     publisher = {{Springer}},
     url = {https://link.springer.com/chapter/10.1007/978-3-030-60990-0_9},
   }

2. Formalizing the Generalization-Forgetting Trade-off in Continual Learning

   Krishnan Raghavan, and Prasanna Balaprakash

   In Advances in Neural Information Processing Systems (AR:20), 2021

   Bib

   @inproceedings{raghavanFormalizingGeneralizationforgettingTradeoff2021,
     title = {Formalizing the Generalization-Forgetting Trade-off in Continual Learning},
     booktitle = {Advances in {{Neural Information Processing Systems}} ({{AR}}:20)},
     author = {Raghavan, Krishnan and Balaprakash, Prasanna},
     year = {2021},
     volume = {34},
     pages = {17284--17297},
   }

3. A Game Theoretic Approach for Addressing Domain-Shift in Big-Data

   Krishnan Raghavan, Sarangapani Jagannathan, and V. A. Samaranayake

   2021

   Bib

   @article{raghavanGameTheoreticApproach2021,
     title = {A {{Game Theoretic Approach}} for {{Addressing Domain-Shift}} in {{Big-Data}}},
     author = {Raghavan, Krishnan and Jagannathan, Sarangapani and Samaranayake, V. A.},
     year = {2021},
     journaltitle = {IEEE Transactions on Big Data (IF: 4.27)},
     volume = {8},
     number = {6},
     pages = {1610--1621},
     publisher = {{IEEE}},
   }

4. Machine-Learning-Based Inversion of Nuclear Responses

   Krishnan Raghavan, Prasanna Balaprakash, Alessandro Lovato, and 2 more authors

   2021

   Bib

   @article{raghavanMachinelearningbasedInversionNuclear2021,
     title = {Machine-Learning-Based Inversion of Nuclear Responses},
     author = {Raghavan, Krishnan and Balaprakash, Prasanna and Lovato, Alessandro and Rocco, Noemi and Wild, Stefan M.},
     year = {2021},
     journaltitle = {Physical Review C (IF: 3.09)},
     volume = {103},
     number = {3},
     pages = {035502},
     publisher = {{APS}},
   }

2022

1. Autodeuq: Automated Deep Ensemble with Uncertainty Quantification

   Romain Egele, Romit Maulik, Krishnan Raghavan, and 3 more authors

   In 26th International Conference on Pattern Recognition (ICPR), 2022

   Bib

   @inproceedings{egeleAutodeuqAutomatedDeep2022,
     title = {Autodeuq: {{Automated}} Deep Ensemble with Uncertainty Quantification},
     shorttitle = {Autodeuq},
     booktitle = {26th {{International Conference}} on {{Pattern Recognition}} ({{ICPR}})},
     author = {Egele, Romain and Maulik, Romit and Raghavan, Krishnan and Lusch, Bethany and Guyon, Isabelle and Balaprakash, Prasanna},
     year = {2022},
     pages = {1908--1914},
     publisher = {{IEEE}},
   }

2. Continual Learning via Dynamic Programming

   Krishnan Raghavan, and Prasanna Balaprakash

   In International Conference on Pattern Recognition, 2022

   Bib

   @inproceedings{raghavanContinualLearningDynamic2022,
     title = {Continual Learning via Dynamic Programming},
     booktitle = {International {{Conference}} on {{Pattern Recognition}}},
     author = {Raghavan, Krishnan and Balaprakash, Prasanna},
     year = {2022},
     url = {https://ieeexplore.ieee.org/document/9956042},
   }

3. Automated Continual Learning of Defect Identification in Coherent Diffraction Imaging

   Orcun Yildiz, Henry Chan, Krishnan Raghavan, and 5 more authors

   In IEEE/ACM International Workshop on Artificial Intelligence and Machine Learning for Scientific Applications (AI4S), 2022

   Abs

   X-ray Bragg coherent diffraction imaging (BCDI) is widely used for materials characterization. However, obtaining X-ray diffraction data is difficult and computationally intensive. Here, we introduce a machine learning approach to identify crystalline line defects in samples from the raw coherent diffraction data. To automate this process, we compose a workflow coupling coherent diffraction data generation with training and inference of deep neural network defect classifiers. In particular, we adopt a continual learning approach, where we generate training and inference data as needed based on the accuracy of the defect classifier instead of all training data generated a priori. The results show that our approach improves the accuracy of defect classifiers while using much fewer samples of data.

2023

1. SF-SFD: Stochastic Optimization of Fourier Coefficients to Generate Space-Filling Designs

   Manisha Garg, Tyler Chang, and Krishnan Raghavan

   In Winter Simulation Conference, Accepted, 2023

   Bib

   @inproceedings{gargSFSFDStochasticOptimization2023,
     title = {{{SF-SFD}}: {{Stochastic Optimization}} of {{Fourier Coefficients}} to {{Generate Space-Filling Designs}}},
     booktitle = {Winter {{Simulation Conference}}, Accepted},
     author = {Garg, Manisha and Chang, Tyler and Raghavan, Krishnan},
     year = {2023},
   }

2. ‪Graph Neural Networks for Detecting Anomalies in Scientific Workflows

   Hongwei Jin, Krishnan Raghavan, George Papadimitriou, and 5 more authors

   2023

   Bib

   @article{jinGraphNeuralNetworks2023,
     title = {‪{{Graph Neural Networks}} for {{Detecting Anomalies}} in {{Scientific Workflows}}},
     author = {Jin, Hongwei and Raghavan, Krishnan and Papadimitriou, George and Wang, Cong and Anirban, Mandal and Mariam, Kiran and Ewa, Deelman and Balaprakash, Prasanna},
     year = {2023},
     journaltitle = {International Journal of high performance computing applications (IF:2.457)},
     url = {https://journals.sagepub.com/doi/abs/10.1177/10943420231172140?journalCode=hpcc},
   }

3. Classification of Events from \\backslashalpha \-Induced Reactions in the MUSIC Detector via Statistical and ML Methods

   Krishnan Raghavan, Melina L. Avila, Prasanna Balaprakash, and 2 more authors

   2023

   Bib

   @article{raghavanClassificationEventsBackslashalpha2023,
     title = {Classification of Events from \$\textbackslash backslashalpha \$-Induced Reactions in the {{MUSIC}} Detector via Statistical and {{ML}} Methods},
     author = {Raghavan, Krishnan and Avila, Melina L. and Balaprakash, Prasanna and Jayatissa, Heshani and Santiago-Gonzalez, Daniel},
     year = {2023},
     journaltitle = {Nuclear Inst. and Methods in Physics Research, A  (IF: 1.335), Accepted},
   }

4. Cooperative Deep Q -Learning Framework for Environments Providing Image Feedback

   Krishnan Raghavan, Vignesh Narayanan, and Sarangapani Jagannathan

   2023

   Bib

   @article{raghavanCooperativeDeepLearning2023,
     title = {Cooperative {{Deep Q}} -{{Learning Framework}} for {{Environments Providing Image Feedback}}},
     author = {Raghavan, Krishnan and Narayanan, Vignesh and Jagannathan, Sarangapani},
     year = {2023},
     journaltitle = {IEEE Transactions on Neural Networks and Learning Systems (IF:11.683), Accepted},
     volume = {0},
     number = {0},
     pages = {0},
     publisher = {{IEEE}},
     doi = {Accepted for Publicatioin},
   }

5. Learning Continually on a Sequence of Graph – The Dynamical System Way

   Krishnan Raghavan, and Prasanna Balaprakash

   2023

   Bib

   @online{raghavanLearningContinuallySequence2023,
     title = {Learning {{Continually}} on a {{Sequence}} of {{Graph}} -- {{The Dynamical System Way}}},
     author = {Raghavan, Krishnan and Balaprakash, Prasanna},
     year = {2023},
     doi = {SIAM Journal on Mathematics of Data Science},
     pubstate = {preprint},
   }

6. Learning to Control Using Image Feedback

   Krishnan Raghavan, Vignesh Narayanan, and Jagannathan Saraangapani

   2023

   Bib

   @online{raghavanLearningControlUsing2023,
     title = {Learning to {{Control}} Using {{Image Feedback}}},
     author = {Raghavan, Krishnan and Narayanan, Vignesh and Saraangapani, Jagannathan},
     year = {2023},
     pubstate = {preprint},
   }