AutoOpt computes per-layer learning rates and momentums that minimize a quadratic approximation of the expected loss one step ahead, and tests the idea on small CNN classifiers.
Stochastic variance reduced multiplicative update for nonnegative matrix fac- torization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2019 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Automatic and Simultaneous Adjustment of Learning Rate and Momentum for Stochastic Gradient Descent
AutoOpt computes per-layer learning rates and momentums that minimize a quadratic approximation of the expected loss one step ahead, and tests the idea on small CNN classifiers.