About
I am a postdoctoral associate at MBZUAI, hosted by Dr. Bin Gu. I obtained a Ph.D. in Machine Learning from the Department of CSE, IIT Kanpur, under the supervision of Dr. Purushottam Kar and Prof. Sandeep K. Shukla. I am interested in developing scalable machine learning / deep learning algorithms with theoretical guarantees on possibly corrupted training and test data, with a broad interest in understanding competing aspects of prediction and security. One of my recent research directions is Spiking Neural Networks, where we studied the implication of this energy-efficient neuronal computational model on generalization and adversarial robustness tasks.
Education
Ph.D. (CSE) Indian Institute of Technology Kanpur, Uttar Pradesh, India 2016-2022
Thesis: Learning in the Presence of an Adversary: A Provable Approach
Advisors: Dr. Purushottam Kar and Prof. Sandeep Kumar Shukla
Received Outstanding PhD Thesis Award (CSE/IITK/2023)
M.Tech. (CSE) PDPM IIITDM Jabalpur, Madhya Pradesh, India 2014-2016
Thesis: Marginal Probability Distribution of Nodes Being Informed in Gossip and Independent Cascade Model
Advisor: Dr. Ruchir Gupta
Received Certificate of Merit for Academic Excellence in Postgraduate (M.Tech/IIITDMJ/2015)
B.Tech. (CSE) Guru Nanak Institute of Technology, West Bengal, India 2007-2011
Research Experience
Postdoctoral Associate MBZUAI, Abu Dhabi Jun'2022 - Present
Research Assistant MBZUAI, Abu Dhabi May'2022 - Jun'2022
Student Research Associate C3I Center, IIT Kanpur Jan'2021 - Dec’2021
Student Research Associate UKICERI, IIT Kanpur Aug’2017 - Dec’2020
Applied Research Scientist Intern Amazon India, Bangalore July'2019 - Oct’2019
Research Intern IBM India Research Lab, Delhi May'2017 -July’2017
Work Experience
Software Engineer Tech Mahindra, Pune April’2012 -Jun’2014
Publications
Conferences (*first co-author)
[ICLR 2024] Bhaskar Mukhoty*, Hilal AlQuabeh*, Giulia De Masi, Huan Xiong, and Bin Gu, Certified adversarial robustness for rate encoded spiking neural networks, in The Twelfth International Conference on Learning Representations (2024) [pdf, poster, code ].
[AAAI 2024] Srinivas Anumasa*, Bhaskar Mukhoty*, Velibor Bojkovic, Giulia De Masi, Huan Xiong, and Bin Gu, "Enhancing training of spiking neural network with stochastic latency", Proceedings of the AAAI Conference on Artificial Intelligence 2024, Vol. 38, No. 10, pp. 10900-10908 [pdf, code].
[AAAI 2024] William de Vazelhes, Bhaskar Mukhoty, Xiaotong Yuan, and Bin Gu, " Iterative regularization with k-support norm: an important complement to sparse recovery", Proceedings of the AAAI Conference on Artificial Intelligence 2024, Vol. 38, No. 10, pp. 11731-11739 [pdf, arxiv, code].
[Neurips 2023] Bhaskar Mukhoty*, Velibor Bojkovic*, William de Vazelhes, Xiaohan Zhao, Giulia De Masi, Huan Xiong, and Bin Gu, "Direct Training of SNN using Local Zeroth Order Method", Thirty-seventh Conference on Neural Information Processing Systems 2023, Vol. 36 [pdf, poster, code].
[ACML 2023] Hilal AlQuabeh, Bhaskar Mukhoty, and Bin Gu, "Variance Reduced Online Gradient Descent for Kernelized Pairwise Learning with Limited Memory", Asian Conference on Machine Learning 2023, pp. 28-43 [pdf, code].
[AAAI 2023] Bhaskar Mukhoty, Debojyoti Dey, and Purushottam Kar, "Corruption-tolerant Algorithms for Generalized Linear Models", Proceedings of the AAAI Conference on Artificial Intelligence 2023, Vol. 37. No. 8, pp. 9243-9250 [pdf, arxiv, slides, code].
[CODS-COMAD 2022] Debojyoti Dey, Bhaskar Mukhoty, and Purushottam Kar, "Agglio: Global optimization for locally convex functions", in 5th Joint International Conference on Data Science & Management of Data (9th ACM IKDD CODS and 27th COMAD) 2022, pp. 37–45 [pdf, arxiv, code].
[AISTATS 2019] Bhaskar Mukhoty, Govind Gopakumar, Prateek Jain, and Purushottam Kar, "Globally convergent iteratively reweighted least squares for robust regression problems", The 22nd International Conference on Artificial Intelligence and Statistics, Vol. 89, pp. 313–322 [pdf, arxiv, poster, code].
[PowerTech 2019] Bhaskar Mukhoty, Vikas Maurya, and Sandeep K Shukla, "Sequence to sequence deep learning models for solar irradiation forecasting", IEEE PowerTech 2019, Milan [link].
[ACSAC 2018] Manish Kesarwani, Bhaskar Mukhoty, Vijay Arya, and Sameep Mehta, "Model extraction warning in mlaas paradigm", Proceedings of the 34th Annual Computer Security Applications Conference 2018, pp. 371-380 [pdf].
Journals
[Machine Learning 2021] Bhaskar Mukhoty, Subhajit Dutta, and Purushottam Kar, "Robust non-parametric regression via incoherent subspace projections", ECML-PKDD 2021, Mach Learn 110, 2941–2989 (2021) [pdf, slides, code].
[TINAE 2020] Amit Chandak, Debojyoti Dey, Bhaskar Mukhoty, and Purushottam Kar, "Epidemiologically and socio-economically optimal policies via bayesian optimization", Transactions of the Indian National Academy of Engineering 5, 117–127 [pdf, code].
[Appl. Intell. 2020] Bhaskar Mukhoty, Ruchir Gupta, K Lakshmanan, and Mayank Kumar, "A parameter-free affinity based clustering", Applied Intelligence 50, 4543–4556[pdf].
[Acta Phy. Pol. B 2016] Anoop Mehta, Bhaskar Mukhoty, and Ruchir Gupta, "Controlling spread of rumor using neighbor centrality", Acta Physica Polonica B 47, 2325–2340 [pdf].
Workshop
[CPSIoTSec 2021] Aneet K Dutta, Bhaskar Mukhoty, and Sandeep K Shukla, Catchall: A robust multivariate intrusion detection system for cyber-physical systems using low rank matrix, in Proceedings of the 2th Workshop on CPS&IoT Security and Privacy, pp. 47-56 [pdf].
Reviewer
Conferences:
NeurIPS 2024 , AISTATS [2022, 2023] , IJCAI-ECAI [2022, 2023], CVIP [2023, 2024], QIP 2022
Journals:
ACM Transactions on Cyber-Physical Systems, The Journal of Supercomputing
Notes: (For personal reference, may contain some errors.)
Contact
Email 1: {firstname}.{lastname}@mbzuai.ac.ae
Email 2: {firstname}.{lastname}@gmail.com