Introduces gradient-enhanced renewable Lasso for high-dimensional GLMs that eliminates batch-number constraints, derives non-asymptotic bounds, and extends to distributed streaming with only gradient exchanges.
arXiv:1806.06761v1 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Renewable Lasso without Batch-Number Constraints: A Gradient-Enhanced Approach
Introduces gradient-enhanced renewable Lasso for high-dimensional GLMs that eliminates batch-number constraints, derives non-asymptotic bounds, and extends to distributed streaming with only gradient exchanges.