Latest work
Statistically and Computationally Efficient Linear Meta-representation Learning
Kiran Thekumparampil, Prateek Jain, Praneeth Netrapalli, Sewoong Oh
Previous version: arXiv preprint arXiv:2105.08306.
Efficient Algorithms for Federated Saddle Point Optimization
Charlie Hou, Kiran K. Thekumparampil, Giulia Fanti, Sewoong Oh
arXiv preprint arXiv:2102.06333.
Optimal Nonsmooth Frank-Wolfe method for Stochastic Regret Minimization
Kiran Thekumparampil, Prateek Jain, Praneeth Netrapalli, Sewoong Oh
Presented at the NeurIPS 2020 workshop on 12th OPT Workshop on
Optimization for Machine Learning (OPT2020)
Peer-reviewed publications
Projection Efficient Subgradient Method and Optimal Nonsmooth Frank-Wolfe Method
(NeurIPS Spotlight talk)
Kiran Thekumparampil, Prateek Jain, Praneeth Netrapalli, Sewoong Oh
In Advances in Neural Information Processing Systems (NeurIPS), 2020.
InfoGAN-CR and ModelCentrality: Self-supervised Model Training and Selection for Disentangling GANs
Zinan Lin, Kiran Thekumparampil, Giulia Fanti, Sewoong Oh
Proceedings of the 37th International Conference on Machine Learning, 2020.
Efficient Algorithms for Smooth Minimax Optimization
Kiran Thekumparampil, Prateek Jain, Praneeth Netrapalli, Sewoong Oh
In Advances in Neural Information Processing Systems (NeurIPS), 2019.
Robustness of conditional GANs to noisy labels
(NeurIPS Spotlight talk)
Kiran K Thekumparampil, Ashish Khetan, Zinan Lin, Sewoong Oh
In Advances in Neural Information Processing Systems (NeurIPS), 2018.
Learning from comparisons and choices
(in alphabetical order) Sahand Negahban, Sewoong Oh, Kiran K Thekumparampil, Jiaming Xu
Journal of Machine Learning Research 19 (40).
Collaboratively learning preferences from ordinal data
(in alphabetical order) Sewoong Oh, Kiran K. Thekumparampil, and Jiaming Xu
In Advances in Neural Information Processing Systems (NIPS), 2015.
Combinatorial resource allocation using submodularity of waterfilling
Kiran Thekumparampil, Andrew Thangaraj, and Rahul Vaze
IEEE Transactions on Wireless Communications 15.1 (2016): 206-216.
Workshop papers
Optimal Nonsmooth Frank-Wolfe method for Stochastic Regret Minimization
Kiran Thekumparampil, Prateek Jain, Praneeth Netrapalli, Sewoong Oh
Presented at the NeurIPS 2020 workshop on 12th OPT Workshop on
Optimization for Machine Learning (OPT2020)
Robust conditional GANs under missing or uncertain labels
Kiran Koshy Thekumparampil, Sewoong Oh, Ashish Khetan
Presented at the ICML 2019 workshop on Uncertainty & Robustness in Deep Learning
Pre-prints and Technical reports
Efficient Algorithms for Federated Saddle Point Optimization
Charlie Hou, Kiran K. Thekumparampil, Giulia Fanti, Sewoong Oh
arXiv preprint arXiv:2102.06333.
Projection Efficient Subgradient Method and Optimal Nonsmooth Frank-Wolfe Method
Kiran Thekumparampil, Prateek Jain, Praneeth Netrapalli, Sewoong Oh
arXiv preprint arXiv:2010.01848.
Efficient Algorithms for Smooth Minimax Optimization
Kiran Thekumparampil, Prateek Jain, Praneeth Netrapalli, Sewoong Oh
arXiv preprint arXiv:1907.01543.
Robust conditional GANs under missing or uncertain labels
Kiran Koshy Thekumparampil, Sewoong Oh, Ashish Khetan
arXiv preprint arXiv:1906.03579.
InfoGAN-CR and ModelCentrality: Self-supervised Model Training and Selection for Disentangling GANs
Zinan Lin, Kiran K. Thekumparampil, Giulia Fanti, Sewoong Oh
arXiv preprint arXiv:1906.06034.
Robustness of conditional GANs to noisy labels
Kiran K Thekumparampil, Ashish Khetan, Zinan Lin, Sewoong Oh
arXiv preprint arXiv:1811.03205.
Attention-based Graph Neural Network for Semi-supervised Learning
Kiran K Thekumparampil, Chong Wang, Sewoong Oh, Li-Jia Li
arXiv preprint arXiv:1803.03735.
Learning from comparisons and choices
(in alphabetical order) Sahand Negahban, Sewoong Oh, Kiran K Thekumparampil, Jiaming Xu
arXiv preprint arXiv:1704.07228.
Sub-Modularity of Waterfilling with Applications to Online Basestation Allocation
Kiran Thekumparampil, Andrew Thangaraj and Rahul Vaze