Kiran Koshy Thekumparampil
5 papers · 2022–2025 · 2 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(10)
Top co-authors
Research topics
Keywords
wasserstein distance
(1)
federated learning
(1)
domain adaptation
(1)
optimal transport
(1)
global optimization
(1)
fisher information matrix
(1)
plackett-luce model
(1)
entropic regularization
(1)
sinkhorn algorithm
(1)
matrix scaling
(1)
convergence rate
(1)
information gain
(1)
memory efficiency
(1)
client heterogeneity
(1)
supervised fine-tuning
(1)
ranking loss
(1)
communication cost
(1)
zeroth-order method
(1)
local optimization
(1)
large language model
(1)
Papers
Comparing Few to Rank Many: Active Human Preference Learning Using Randomized Frank-Wolfe Method
ICML 2025
FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain
ICML 2025
Accelerating Sinkhorn algorithm with sparse Newton iterations
ICLR 2024
DPZero: Private Fine-Tuning of Language Models without Backpropagation
ICML 2024
FedChain: Chained Algorithms for Near-optimal Communication Cost in Federated Learning
ICLR 2022