18. On the Convergence Analysis of Asynchronous SGD for Solving Consistent Linear Systems, Atal Narayan Sahu, Aritra Dutta, Aasutosh Tiwari, and Peter Richtárik, Linear Algebra and its Applications---Elsevier, December 2022. [PDF, PDF-Journal pre-proof]
17. Direct Non-linear Acceleration, Aritra Dutta, El Houcine Bergou, Yunming Xiao, MarcoCanini, and Peter Richtárik, EURO Journal on Computational Optimization- Elsevier, Accepted for publication, October 2022. [PDF]
16. DeepReduce: A Sparse-tensor Communication Framework for Federated Deep Learning, Hang Xu, Kelly Kostopoulou, Aritra Dutta, Xin Li, Alexandros Ntoulas, Panos Kalnis, Thirty-Fifth Conference on Neural Information Processing Systems, 2021. [PDF, Code, Supplementary]
15. Rethinking gradient sparsification as total error minimization, Atal Narayan Sahu, Aritra Dutta, Ahmed M. Abdelmoniem, Trambak Banerjee, Marco Canini, Panos Kalnis, Thirty-Fifth Conference on Neural Information Processing Systems, 2021. (Spotlight) [PDF, Code, Supplementary]
14. GRACE: A Compressed Communication Framework for Distributed Machine Learning, Hang Xu, Chen-Yu Ho, Ahmed M Abdelmoniem, Aritra Dutta, El Houcine Bergou, Marco Canini, Panos Kalnis, Proceedings of 41st IEEE International Conference on Distributed Computing Systems (ICDCS), pp. 561-572, July 2021. [PDF, Codebase-GRACE, IJCAI Tutorial Slides, IJCAI Tutorial Webpage ]
13. Huffman Coding Based Encoding Techniques for Fast Distributed Deep Learning, Rishikesh R Gajjala, Shashwat Banchhor, Ahmed M Abdelmoniem, Aritra Dutta, Marco Canini, Panos Kalnis, Proceedings of ACM CoNEXT 1st Workshop on Distributed Machine Learning (DistributedML '20), pp. 21-27, December 2020. [PDF, CODE]
12. Best Pair Formulation & Accelerated Scheme for Non-convex Principal Component Pursuit, Aritra Dutta, Filip Hanzely, Jingwei Liang, Peter Richtárik, IEEE Transactions on Signal Processing, 68, pp. 6128-6141, 2020. [PDF, CODE]
11. On the Discrepancy between the Theoretical Analysis and Practical Implementations of Compressed Communication for Distributed Deep Learning, Aritra Dutta, El Houcine Bergou, Ahmed M. Abdelmoniem, Chen-Yu Ho, Atal Narayan Sahu, Marco Canini, and Panos Kalnis, In the proceedings of Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20), 34 (04), pp. 3817-3824, 2020. [PDF, PDF+Supplementary Version, CODE, Media Coverage]
10. A Non-convex Projection Method for Robust PCA, Aritra Dutta, Filip Hanzley, and Peter Richtárik, In the proceedings of Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19), 33(01), pp. 1468-1476, January 2019. (Oral Presentation)[PDF, CODE, Full ArXiv Version, Video Demo]
9. Online and Batch Supervised Background Estimation via L1 Regression, Aritra Dutta and Peter Richtárik, In the proceedings of WACV 2019 – IEEE Winter Conference on the Applications of Computer Vision, pp. 541-550, January 2019. [PDF, Supplementary, Code, Video Demo]
8. A Fast Weighted SVT Algorithm, Aritra Dutta and Xin Li, In proceedings of IEEE 5th International Conference on Systems and Informatics (ICSAI 2018), pp. 1022-1026, 2018. [PDF]
7. A Batch-Incremental Video Background Estimation Model using Weighted Low-Rank Approximation of Matrices, Aritra Dutta, Xin Li, and Peter Richtárik, In proceedings of IEEE International Conference on Computer Vision Workshops (ICCVW), pp. 1835–1843, IEEE Xplore, 2017. [PDF]
6. Weighted Low Rank Approximation for Background Estimation Problems, Aritra Dutta and Xin Li, In proceedings of IEEE International Conference on Computer Vision Workshops (ICCVW), pp. 1853–1861, IEEE Xplore, 2017. [PDF, CODE]
5. Fast Detection of Compressively-Sensed IR Targets Using Stochastically Trained Least Squares and Compressed Quadratic Correlation Filter, Brian Millikan, Aritra Dutta, Qiyu Sun, and Hassan Foroosh, IEEE Transactions on Aerospace and Electronic Systems, Vol. 53, Issue 5 , pp. 2449–2461, 2017. [PDF]
4. Shrinkage Function and Its Applications in Matrix Approximations, Toby Boas, Aritra Dutta, Xin Li, Katie Mercier, and Eric Niderman, Electronic Journal of Linear Algebra, Vol. 32, pp. 163–171, 2017. [PDF]
3. On a Problem of Weighted Low Rank Approximation of Matrices, Aritra Dutta and Xin Li, SIAM Journal on Matrix Analysis and Applications, Vol. 38, No. 2, pp. 530–553, 2017. [PDF, CODE]
2. A Fast Algorithm for a Special Weighted Low Rank Approximation, Aritra Dutta and Xin Li, 15th IAPR International Conference on Machine Vision Applications (MVA), IEEE Xplore, pp. 93-96, 2017. [PDF]
1. Initialized Iterative Reweighted Least Squares for Automatic Target Recognition, Brian Millikan, Aritra Dutta, Nazanin Rahnavard, Qiyu Sun, and Hassan Foroosh, In proceedings of IEEE Military Communications Conference 2015, pp. 506-510, 2015. [PDF]
17. Direct Non-linear Acceleration, Aritra Dutta, El Houcine Bergou, Yunming Xiao, MarcoCanini, and Peter Richtárik, EURO Journal on Computational Optimization- Elsevier, Accepted for publication, October 2022. [PDF]
16. DeepReduce: A Sparse-tensor Communication Framework for Federated Deep Learning, Hang Xu, Kelly Kostopoulou, Aritra Dutta, Xin Li, Alexandros Ntoulas, Panos Kalnis, Thirty-Fifth Conference on Neural Information Processing Systems, 2021. [PDF, Code, Supplementary]
15. Rethinking gradient sparsification as total error minimization, Atal Narayan Sahu, Aritra Dutta, Ahmed M. Abdelmoniem, Trambak Banerjee, Marco Canini, Panos Kalnis, Thirty-Fifth Conference on Neural Information Processing Systems, 2021. (Spotlight) [PDF, Code, Supplementary]
14. GRACE: A Compressed Communication Framework for Distributed Machine Learning, Hang Xu, Chen-Yu Ho, Ahmed M Abdelmoniem, Aritra Dutta, El Houcine Bergou, Marco Canini, Panos Kalnis, Proceedings of 41st IEEE International Conference on Distributed Computing Systems (ICDCS), pp. 561-572, July 2021. [PDF, Codebase-GRACE, IJCAI Tutorial Slides, IJCAI Tutorial Webpage ]
13. Huffman Coding Based Encoding Techniques for Fast Distributed Deep Learning, Rishikesh R Gajjala, Shashwat Banchhor, Ahmed M Abdelmoniem, Aritra Dutta, Marco Canini, Panos Kalnis, Proceedings of ACM CoNEXT 1st Workshop on Distributed Machine Learning (DistributedML '20), pp. 21-27, December 2020. [PDF, CODE]
12. Best Pair Formulation & Accelerated Scheme for Non-convex Principal Component Pursuit, Aritra Dutta, Filip Hanzely, Jingwei Liang, Peter Richtárik, IEEE Transactions on Signal Processing, 68, pp. 6128-6141, 2020. [PDF, CODE]
11. On the Discrepancy between the Theoretical Analysis and Practical Implementations of Compressed Communication for Distributed Deep Learning, Aritra Dutta, El Houcine Bergou, Ahmed M. Abdelmoniem, Chen-Yu Ho, Atal Narayan Sahu, Marco Canini, and Panos Kalnis, In the proceedings of Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20), 34 (04), pp. 3817-3824, 2020. [PDF, PDF+Supplementary Version, CODE, Media Coverage]
10. A Non-convex Projection Method for Robust PCA, Aritra Dutta, Filip Hanzley, and Peter Richtárik, In the proceedings of Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19), 33(01), pp. 1468-1476, January 2019. (Oral Presentation)[PDF, CODE, Full ArXiv Version, Video Demo]
9. Online and Batch Supervised Background Estimation via L1 Regression, Aritra Dutta and Peter Richtárik, In the proceedings of WACV 2019 – IEEE Winter Conference on the Applications of Computer Vision, pp. 541-550, January 2019. [PDF, Supplementary, Code, Video Demo]
8. A Fast Weighted SVT Algorithm, Aritra Dutta and Xin Li, In proceedings of IEEE 5th International Conference on Systems and Informatics (ICSAI 2018), pp. 1022-1026, 2018. [PDF]
7. A Batch-Incremental Video Background Estimation Model using Weighted Low-Rank Approximation of Matrices, Aritra Dutta, Xin Li, and Peter Richtárik, In proceedings of IEEE International Conference on Computer Vision Workshops (ICCVW), pp. 1835–1843, IEEE Xplore, 2017. [PDF]
6. Weighted Low Rank Approximation for Background Estimation Problems, Aritra Dutta and Xin Li, In proceedings of IEEE International Conference on Computer Vision Workshops (ICCVW), pp. 1853–1861, IEEE Xplore, 2017. [PDF, CODE]
5. Fast Detection of Compressively-Sensed IR Targets Using Stochastically Trained Least Squares and Compressed Quadratic Correlation Filter, Brian Millikan, Aritra Dutta, Qiyu Sun, and Hassan Foroosh, IEEE Transactions on Aerospace and Electronic Systems, Vol. 53, Issue 5 , pp. 2449–2461, 2017. [PDF]
4. Shrinkage Function and Its Applications in Matrix Approximations, Toby Boas, Aritra Dutta, Xin Li, Katie Mercier, and Eric Niderman, Electronic Journal of Linear Algebra, Vol. 32, pp. 163–171, 2017. [PDF]
3. On a Problem of Weighted Low Rank Approximation of Matrices, Aritra Dutta and Xin Li, SIAM Journal on Matrix Analysis and Applications, Vol. 38, No. 2, pp. 530–553, 2017. [PDF, CODE]
2. A Fast Algorithm for a Special Weighted Low Rank Approximation, Aritra Dutta and Xin Li, 15th IAPR International Conference on Machine Vision Applications (MVA), IEEE Xplore, pp. 93-96, 2017. [PDF]
1. Initialized Iterative Reweighted Least Squares for Automatic Target Recognition, Brian Millikan, Aritra Dutta, Nazanin Rahnavard, Qiyu Sun, and Hassan Foroosh, In proceedings of IEEE Military Communications Conference 2015, pp. 506-510, 2015. [PDF]
PHD Thesis
Weighted Low-Rank Approximation of Matrices: Some Analytical and Numerical Aspects, Aritra Dutta, Ph.D. Dissertation, Department of Mathematics, University of Central Florida. [PDF]
Preprints/Initial Works (In reverse chronological order)
4. Personalized Federated Learning with Communication Compression, El Houcine Bergou, Konstantin Burlachenko, Aritra Dutta, Peter Richtárik, September 2022. [PDF, Code]
3. A Fast and Adaptive SVD-free Algorithm for General Weighted Low-rank Recovery, Aritra Dutta, Jingwei Liang, Xin Li, January 2021 (revised August 2022). [PDF, Code]
2. DeepReduce: A Sparse-tensor Communication Framework for Distributed Deep Learning, Kelly Kostopoulou, Hang Xu, Aritra Dutta, Xin Li, Alexandros Ntoulas, Panos Kalnis, February 2021. [PDF, CODE, Experimental Results]
1. Compressed Communication for Distributed Deep Learning: Survey and Quantitative Evaluation Hang Xu, Chen-Yu Ho, Ahmed Mohammed Abdelmoneim Sayed, Aritra Dutta, El Houcine Bergou, Konstantinos Karatsenidis, Marco Canini, Panos Kalnis, April 2020. [PDF, codebase-GRACE, IJCAI Tutorial Slides, IJCAI Tutorial Webpage]
3. A Fast and Adaptive SVD-free Algorithm for General Weighted Low-rank Recovery, Aritra Dutta, Jingwei Liang, Xin Li, January 2021 (revised August 2022). [PDF, Code]
2. DeepReduce: A Sparse-tensor Communication Framework for Distributed Deep Learning, Kelly Kostopoulou, Hang Xu, Aritra Dutta, Xin Li, Alexandros Ntoulas, Panos Kalnis, February 2021. [PDF, CODE, Experimental Results]
1. Compressed Communication for Distributed Deep Learning: Survey and Quantitative Evaluation Hang Xu, Chen-Yu Ho, Ahmed Mohammed Abdelmoneim Sayed, Aritra Dutta, El Houcine Bergou, Konstantinos Karatsenidis, Marco Canini, Panos Kalnis, April 2020. [PDF, codebase-GRACE, IJCAI Tutorial Slides, IJCAI Tutorial Webpage]
Technical Reports
- Weighted Low-Rank Approximation for Background Modeling, Aritra Dutta, Xin Li, and Peter Richtárik, April 2018. [PDF, CODE, Video Demo]
- Weighted Singular Value Thresholding and its Applications to Background Estimation, Aritra Dutta, Boquing Gong, Xin Li, and Mubarak Shah, January 2017. [PDF, CODE] (On A Weighted Singular Value Thresholding Problem, Aritra Dutta, Boqing Gong, Xin Li, and Mubarak Shah, January 2019. [PDF, CODE])
- Image Compression Using Simulated Annealing, Aritra Dutta, Geonwoo Kim, Meiqin Li, Carlos Ortiz Marrero, Mohit Sinha, Cole Stieglerk, Mathematical Modeling in Industry XIX, Institute of Mathematics and its Applications, August 2015. [PDF,Presentation]
- Efficient and robust solution strategies for saddle-point systems, Jeremy Chiu, Lola Davidson, Aritra Dutta, Jia Gou, Kak Choon Loy, Mark Thom, Dimitar Trenev, Mathematical Modeling in Industry XVIII, Institute of Mathematics and its Applications Preprint Series 2440, October 2014. [PDF, Presentation]