A meta-distribution-based robust optimization method learns RKHS uncertainty sets from relevant sources to guarantee out-of-distribution performance on unseen target distributions.
Agnostic federated learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Position paper claiming that distributed training across massive edge devices can overcome data depletion and centralized compute monopolies in LLM scaling.
citing papers explorer
-
Robust Out-of-Distribution Stochastic Optimization
A meta-distribution-based robust optimization method learns RKHS uncertainty sets from relevant sources to guarantee out-of-distribution performance on unseen target distributions.
-
Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices
Position paper claiming that distributed training across massive edge devices can overcome data depletion and centralized compute monopolies in LLM scaling.