VISTA adaptively tunes consistency thresholds in decentralized SGD so that the system converges asymptotically like standard SGD even when adversaries dominate the worker pool.
Some methods of speeding up the convergence of iteration methods.USSR Computational Mathematics and Mathematical Physics, 4(5):1–17
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
method 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3representative citing papers
CRAFT derives a closed-form solution for conflict-resolved aggregation in federated learning via geometric constraints and projection, with theoretical support for common descent and empirical gains on heterogeneous data.
mQO combines differentiable QUBO optimization with mutation-based resets and local search to outperform heuristics and solvers on large-scale combinatorial problems by addressing stalling in local maxima.
citing papers explorer
-
\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.
-
CRAFT: Conflict-Resolved Aggregation for Federated Training
CRAFT derives a closed-form solution for conflict-resolved aggregation in federated learning via geometric constraints and projection, with theoretical support for common descent and empirical gains on heterogeneous data.
-
Mutation-Guided Differentiable Quadratic Combinatorial Optimization
mQO combines differentiable QUBO optimization with mutation-based resets and local search to outperform heuristics and solvers on large-scale combinatorial problems by addressing stalling in local maxima.