Ketan Rajawat
4 papers · 2021–2024 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🌍
Conference Polyglot
(3)
🐝
Cross-Pollinator
(7)
Conferences
ICML (2)
AISTATS (1)
NIPS (1)
Top co-authors
Keywords
federated learning
(2)
stochastic optimization
(2)
quasi-newton method
(2)
superlinear convergence
(2)
numerical optimization
(1)
hessian approximation
(1)
communication efficiency
(1)
convergence rate
(1)
incremental optimization
(1)
alternating direction method of multiplier
(1)
bfgs method
(1)
momentum method
(1)
stochastic quantization
(1)
newton-type method
(1)
quadratic convergence
(1)
sample complexity
(1)
communication complexity
(1)
Papers
Sharpened Lazy Incremental Quasi-Newton Method
AISTATS 2024
FedNew: A Communication-Efficient and Privacy-Preserving Newton-Type Method for Federated Learning
ICML 2022
Sharpened Quasi-Newton Methods: Faster Superlinear Rate and Larger Local Convergence Neighborhood
ICML 2022
STEM: A Stochastic Two-Sided Momentum Algorithm Achieving Near-Optimal Sample and Communication Complexities for Federated Learning
NIPS 2021