Kiran Koshy Thekumparampil

39 papers A* 11A 1Journal 26Unranked 1

Year	Rank	Type	Title / Venue / Authors
2025	A*	`conf`	Comparing Few to Rank Many: Active Human Preference Learning Using Randomized Frank-Wolfe Method. ICML Kiran Koshy Thekumparampil, Gaurush Hiranandani, Kousha Kalantari, Shoham Sabach, Branislav Kveton
2025	J	`jnl`	ConMeZO: Adaptive Descent-Direction Sampling for Gradient-Free Finetuning of Large Language Models. CoRR Lejs Deen Behric, Liang Zhang, Bingcong Li, Kiran Koshy Thekumparampil
2025	A*	`conf`	FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain. ICML Rohan Deb, Kiran Koshy Thekumparampil, Kousha Kalantari, Gaurush Hiranandani, Shoham Sabach, Branislav Kveton
2025	J	`jnl`	FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain. CoRR Rohan Deb, Kiran Koshy Thekumparampil, Kousha Kalantari, Gaurush Hiranandani, Shoham Sabach, Branislav Kveton
2025	J	`jnl`	RewardRank: Optimizing True Learning-to-Rank Utility. CoRR Gaurav Bhatt, Kiran Koshy Thekumparampil, Tanmay Gangwani, Tesi Xiao, Leonid Sigal
2025	J	`jnl`	Zeroth-Order Optimization Finds Flat Minima. CoRR Liang Zhang, Bingcong Li, Kiran Koshy Thekumparampil, Sewoong Oh, Michael Muehlebach, Niao He
2024	J	`jnl`	A Sinkhorn-type Algorithm for Constrained Optimal Transport. CoRR Xun Tang, Holakou Rahmanian, Michael Shavlovsky, Kiran Koshy Thekumparampil, Tesi Xiao, Lexing Ying
2024	J	`jnl`	Accelerating Sinkhorn Algorithm with Sparse Newton Iterations. CoRR Xun Tang, Michael Shavlovsky, Holakou Rahmanian, Elisa Tardini, Kiran Koshy Thekumparampil, Tesi Xiao, Lexing Ying
2024	A*	`conf`	Accelerating Sinkhorn algorithm with sparse Newton iterations. ICLR Xun Tang, Michael Shavlovsky, Holakou Rahmanian, Elisa Tardini, Kiran Koshy Thekumparampil, Tesi Xiao, Lexing Ying
2024	J	`jnl`	Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe. CoRR Kiran Koshy Thekumparampil, Gaurush Hiranandani, Kousha Kalantari, Shoham Sabach, Branislav Kveton
2024	A*	`conf`	DPZero: Private Fine-Tuning of Language Models without Backpropagation. ICML Liang Zhang, Bingcong Li, Kiran Koshy Thekumparampil, Sewoong Oh, Niao He
2024	J	`jnl`	Pretrained deep models outperform GBDTs in Learning-To-Rank under label scarcity. Trans. Mach. Learn. Res. Charlie Hou, Kiran Koshy Thekumparampil, Michael Shavlovsky, Giulia Fanti, Yesh Dattatreya, Sujay Sanghavi
2023	J	`jnl`	DPZero: Dimension-Independent and Differentially Private Zeroth-Order Optimization. CoRR Liang Zhang, Kiran Koshy Thekumparampil, Sewoong Oh, Niao He
2023	J	`jnl`	Pretrained deep models outperform GBDTs in Learning-To-Rank under label scarcity. CoRR Charlie Hou, Kiran Koshy Thekumparampil, Michael Shavlovsky, Giulia Fanti, Yesh Dattatreya, Sujay Sanghavi
2022	A*	`conf`	Bring Your Own Algorithm for Optimal Differentially Private Stochastic Minimax Optimization. NeurIPS Liang Zhang, Kiran Koshy Thekumparampil, Sewoong Oh, Niao He
2022	J	`jnl`	Bring Your Own Algorithm for Optimal Differentially Private Stochastic Minimax Optimization. CoRR Liang Zhang, Kiran Koshy Thekumparampil, Sewoong Oh, Niao He
2022	A*	`conf`	FedChain: Chained Algorithms for Near-optimal Communication Cost in Federated Learning. ICLR Charlie Hou, Kiran Koshy Thekumparampil, Giulia Fanti, Sewoong Oh
2022	A	`conf`	Lifted Primal-Dual Method for Bilinearly Coupled Smooth Minimax Optimization. AISTATS Kiran Koshy Thekumparampil, Niao He, Sewoong Oh
2022	J	`jnl`	Lifted Primal-Dual Method for Bilinearly Coupled Smooth Minimax Optimization. CoRR Kiran Koshy Thekumparampil, Niao He, Sewoong Oh
2021	J	`jnl`	Efficient Algorithms for Federated Saddle Point Optimization. CoRR Charlie Hou, Kiran Koshy Thekumparampil, Giulia Fanti, Sewoong Oh
2021	J	`jnl`	Reducing the Communication Cost of Federated Learning through Multistage Optimization. CoRR Charlie Hou, Kiran Koshy Thekumparampil, Giulia Fanti, Sewoong Oh
2021	J	`jnl`	Sample Efficient Linear Meta-Learning by Alternating Minimization. CoRR Kiran Koshy Thekumparampil, Prateek Jain, Praneeth Netrapalli, Sewoong Oh
2021	A*	`conf`	Statistically and Computationally Efficient Linear Meta-representation Learning. NeurIPS Kiran Koshy Thekumparampil, Prateek Jain, Praneeth Netrapalli, Sewoong Oh
2020	A*	`conf`	InfoGAN-CR and ModelCentrality: Self-supervised Model Training and Selection for Disentangling GANs. ICML Zinan Lin, Kiran Koshy Thekumparampil, Giulia Fanti, Sewoong Oh
2020	A*	`conf`	Projection Efficient Subgradient Method and Optimal Nonsmooth Frank-Wolfe Method. NeurIPS Kiran Koshy Thekumparampil, Prateek Jain, Praneeth Netrapalli, Sewoong Oh
2020	J	`jnl`	Projection Efficient Subgradient Method and Optimal Nonsmooth Frank-Wolfe Method. CoRR Kiran Koshy Thekumparampil, Prateek Jain, Praneeth Netrapalli, Sewoong Oh
2019	A*	`conf`	Efficient Algorithms for Smooth Minimax Optimization. NeurIPS Kiran Koshy Thekumparampil, Prateek Jain, Praneeth Netrapalli, Sewoong Oh
2019	J	`jnl`	Efficient Algorithms for Smooth Minimax Optimization. CoRR Kiran Koshy Thekumparampil, Prateek Jain, Praneeth Netrapalli, Sewoong Oh
2019	J	`jnl`	InfoGAN-CR: Disentangling Generative Adversarial Networks with Contrastive Regularizers. CoRR Zinan Lin, Kiran Koshy Thekumparampil, Giulia Fanti, Sewoong Oh
2019	J	`jnl`	Robust conditional GANs under missing or uncertain labels. CoRR Kiran Koshy Thekumparampil, Sewoong Oh, Ashish Khetan
2018	J	`jnl`	Attention-based Graph Neural Network for Semi-supervised Learning. CoRR Kiran Koshy Thekumparampil, Chong Wang, Sewoong Oh, Li-Jia Li
2018	J	`jnl`	Learning from Comparisons and Choices. J. Mach. Learn. Res. Sahand Negahban, Sewoong Oh, Kiran Koshy Thekumparampil, Jiaming Xu
2018	J	`jnl`	Robustness of Conditional GANs to Noisy Labels. CoRR Kiran Koshy Thekumparampil, Ashish Khetan, Zinan Lin, Sewoong Oh
2018	A*	`conf`	Robustness of conditional GANs to noisy labels. NeurIPS Kiran Koshy Thekumparampil, Ashish Khetan, Zinan Lin, Sewoong Oh
2017	J	`jnl`	Learning from Comparisons and Choices. CoRR Sahand Negahban, Sewoong Oh, Kiran Koshy Thekumparampil, Jiaming Xu
2016	J	`jnl`	Combinatorial Resource Allocation Using Submodularity of Waterfilling. IEEE Trans. Wirel. Commun. Kiran Koshy Thekumparampil, Andrew Thangaraj, Rahul Vaze
2015	—	`conf`	Collaboratively Learning Preferences from Ordinal Data. NIPS Sewoong Oh, Kiran Koshy Thekumparampil, Jiaming Xu
2015	J	`jnl`	Collaboratively Learning Preferences from Ordinal Data. CoRR Sewoong Oh, Kiran Koshy Thekumparampil, Jiaming Xu
2014	J	`jnl`	Sub-Modularity of Waterfilling with Applications to Online Basestation Allocation. CoRR Kiran Koshy Thekumparampil, Andrew Thangaraj, Rahul Vaze