A new algorithm for the incomplete-information game of coding learns adversary preferences through repeated interactions and achieves sublinear cumulative regret by focusing search on promising acceptance rules.
General coded computing: Adversarial settings
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.IT 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
The GMUDC framework provides topology-aware upper and lower bounds on reconstruction risk for nonlinear functions in RKHS under per-server computation and communication budgets in both quenched and annealed regimes.
citing papers explorer
-
Learning from Acceptance: Cumulative Regret in the Game of Coding
A new algorithm for the incomplete-information game of coding learns adversary preferences through repeated interactions and achieves sublinear cumulative regret by focusing search on promising acceptance rules.
-
General Multi-User Distributed Computing: A Learning-Theoretic RKHS Framework for Generic Nonlinear Target Functions with Topology-Aware Risk Analysis
The GMUDC framework provides topology-aware upper and lower bounds on reconstruction risk for nonlinear functions in RKHS under per-server computation and communication budgets in both quenched and annealed regimes.