A min-rule distributed learning algorithm for hypothesis testing achieves network-independent exponential convergence rates and Byzantine resilience, outperforming belief-averaging methods.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2019 3verdicts
UNVERDICTED 3representative citing papers
Conditional mutual information bounds ideal prediction errors for feature subsets and supplies a stopping condition for greedy selection algorithms.
Approximate minimax theorems are shown for the finite blocklength lossy JSCC game over an AVC, with minimax and maximin values coinciding asymptotically and at second order around a critical rate threshold.
citing papers explorer
-
A New Approach to Distributed Hypothesis Testing and Non-Bayesian Learning: Improved Learning Rate and Byzantine-Resilience
A min-rule distributed learning algorithm for hypothesis testing achieves network-independent exponential convergence rates and Byzantine resilience, outperforming belief-averaging methods.
-
Feature Selection via Mutual Information: New Theoretical Insights
Conditional mutual information bounds ideal prediction errors for feature subsets and supplies a stopping condition for greedy selection algorithms.
-
Minimax Theorems for Finite Blocklength Lossy Joint Source-Channel Coding over an AVC
Approximate minimax theorems are shown for the finite blocklength lossy JSCC game over an AVC, with minimax and maximin values coinciding asymptotically and at second order around a critical rate threshold.