Geometric step decay yields local linear convergence for stochastic algorithms on sharp nonconvex problems and gives matching or new guarantees for phase retrieval and blind deconvolution under Gaussian and heavy-tailed measurements.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2019 2verdicts
UNVERDICTED 2representative citing papers
Machine learning models using text, user, and network attributes classify Twitter users as bullies or aggressors with over 90% accuracy and AUC.
citing papers explorer
-
Stochastic algorithms with geometric step decay converge linearly on sharp functions
Geometric step decay yields local linear convergence for stochastic algorithms on sharp nonconvex problems and gives matching or new guarantees for phase retrieval and blind deconvolution under Gaussian and heavy-tailed measurements.
-
Detecting Cyberbullying and Cyberaggression in Social Media
Machine learning models using text, user, and network attributes classify Twitter users as bullies or aggressors with over 90% accuracy and AUC.