Publications

Journals and Book Chapters

1. S.Dhar, J.Guo, J. Liu, S. Tripathi, U. Kurup, M. Shah, On-Device Machine Learning: An Algorithms and Learning Theory Perspective. ACM TIOT 2021 (to appear).

2. V. Cherkassky, S. Dhar, “Interpretation of Black-Box Predictive Models”. Measures of Complexity: Festschrift for Alexey Chervonenkis (Editors: V. Vovk , H. Papadopoulos, A. Gammerman), Oct 2015. ( other versions)

3. S. Dhar, V. Cherkassky, “Development and Evaluation of Cost-Sensitive Universum SVM”, IEEE Transactions on Systems, MAN, and Cybernetics PART B: Cybernetics, vol. 45, no. 4, pp. 806-817, Apr 2015.

4. A. Jonson, E. Dickson, H. Shiao, V. Cherkassky, S. Dhar, L. Downs Jr,“Machine learning as a tool to predict survival outcomes for carcinosarcoma of the female genital tract”,Gynecologic Oncology, Volume 123 (2), November 2011.

5. V. Cherkassky, S. Dhar, and W. Dai, “Practical Conditions for Effectiveness of the Universum Learning,” IEEE Transactions on Neural Networks, vol.22, no. 8, pp. 1241-1255, Aug 2011.

Conferences

1. S. Dhar, J. Heydari, S. Tripathi, U. Kurup, M. Shah, “Evolving GANs: When Contradictions Turn into Compliance”, (preprint)

2. S. Dhar, B. Gonazales, “Deep One Class Classification using Contradictions”, (preprint)

3. Samarth Tripathi, Jiayi Liu, S. Dhar, Unmesh Kurup, Mohak Shah, “Improving Model Training by Periodic Sampling over Weight Distributions” IEEE Big Data 2020.

4. N. Ramakrishnan, S.Dhar, J. Irion, “Scalable Graph SLAM for HD Maps”, 2021 (US Patent App, WO Patent)

5. S.Dhar, U.Kurup, M.Shah, “Stabilizing Bi-Level Hyperparameter Optimization using Moreau-Yosida Regularization,” ICML 2020 (AutoML Workshop).

6. S.Dhar, U.Kurup, M.Shah, “Moreau-Yosida Regularized Bi-Level Hyperparameter Optimization,” KDD 2020 (AutoML Workshop).

7. Y. Park, S. Dhar, S. Boyd, M. Shah, “Variable Metric Proximal Gradient Method with Diagonal Barzilai-Borwein Step size” ICASSP 2020.

8. S. Dhar, V. Cherkassky, M.Shah, “Multiclass Learning from Contradictions”, NeuRIPS 2019.

9. S. Dhar, V. Cherkassky, “Single-Class Universum SVM” preprint

10. Y. Park, S.Dhar, S. Boyd, M. Shah, “Variable Metric Proximal Gradient Method with Diagonal Barzilai-Borwein Stepsize”, NIPS workshop on Optimization for Machine Learning, 2017

11. S. Dhar, V. Cherkassky, “Universum learning for SVM regression”, IJCNN 2017.

12. S. Dhar et. al “On Multiclass Universum Learning”, NIPS workshop on Learning in High Dimensions with Structure, 2016.

13. S. Dhar, C. Yi, N. Ramakrishnan, and M. Shah, “ADMM based Scalable Machine Learning on Spark”, IEEE Big Data 2015 , Santa Clara, 2015.

14. M.Ganser, S. Dhar, U. Kurup, C.Cunha, and A.Gacic, “A Data-Driven approach towards Patient Identification for Tele-health Programs”, IEEE Big Data 2015 (Workshop on Mining Big Data to Improve Clinical Effectiveness).

15. S. Dhar, and V. Cherkassky, “Cost-Sensitive Universum-SVM”, ICMLA, 2012.

16. V. Cherkassky, and S. Dhar, “Market Timing of International Mutual Funds: A Decade after the Scandal”, IEEE Computational Intelligence for Financial Engineering & Economics, 2012.

17. S. Dhar, V. Cherkassky, “Practical Analysis of the Universum SVM Learning”,Snowbird Learning Workshop, April 2011.

18. S. Dhar, V. Cherkassky, “Application of SOM to Analysis of Minnesota Soil Survey Data”, International Joint Conference on Neural Networks (IJCNN), Feb 2011.

19. V. Cherkassky, S. Dhar, “Simple Method for Interpretation of High-Dimensional Nonlinear SVM Classification Models”, Proceedings of the 2010 International Conference on Data Mining, July 2010.

20. S. Dhar and M. Paul, “Adaptive Pseudo-OFDM based WLAN Systems using Neural Network”, IEEE International conference on Wireless Communication & Sensor Networks, December 17-19, 2006.

Technical Reports \ Posters \ Tutorials \ Talks

1. S. Dhar, M. Shah, “ADMM Based Scalable Machine Learning on APache Spark”. Spark Summit 2017 Talk

2. S.Dhar, N. Ramakrishnan,V. Cherkassky, and M. Shah, “Universum Learning for Multiclass SVM”

3. G. Kamath, S. Dhar, N. Ramakrishnan, D. Hallac, J. Leskovec, M. Shah, “Scalable Machine Learning on Spark for multiclass problems”, Baylearn 2016. abstract,poster

4. S. Dhar and V. Cherkassky, “Universum Learning for SVM Regression”

5. V. Cherkassky and S. Dhar,“Advances in Universum Learning”, IJCNN 2015. (tutorial)

6. M. Ganser, S. Dhar, U. Kurup, C. Cunha, and A. Gacic, “Patient Identification for Telehealth Programs”, ICMLA 2015. (Poster)

7. S. Dhar, and E. Cherkassky, “Machine Learning for Evidence-Based Medical Diagnosis”, IEM Innovation Showcase, Minnesota, Sept 11, 2012. (Poster)

8. S. Dhar, V. Cherkassky, “Statistical Analysis of the Soil Chemical Survey Data”, Report no. Mn/DOT 2010-22, June 2010. ( Technical Report)

9. S. Dhar, V. Cherkassky, R. Edstrom, J. Seaberg, S. Hennes, “Exploring the Pattern of Clustering within Minnesota Soil Survey Data using Self Organizing Maps”, 21st AnnualCTS Transportation Research Conference. River Centre, St. Paul, MN. April 2010. (Poster)