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.
Game of coding: Sybil resistant decentralized machine learning with minimal trust assumption
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
extension 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Equilibria and optimal strategies are characterized for a two-repetition vector coding game in Euclidean space with one rational adversary.
VISTA adaptively tunes consistency thresholds in decentralized SGD so that the system converges asymptotically like standard SGD even when adversaries dominate the worker pool.
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.
-
Game of Coding for Vector-Valued Computations
Equilibria and optimal strategies are characterized for a two-repetition vector coding game in Euclidean space with one rational adversary.
-
\mathsf{VISTA}: Decentralized Machine Learning in Adversary Dominated Environments
VISTA adaptively tunes consistency thresholds in decentralized SGD so that the system converges asymptotically like standard SGD even when adversaries dominate the worker pool.