L-BFGS with line search or trust region is applied to deep learning and deep Q-learning, with convergence theorems that rely on strong convexity and mixed empirical results on MNIST and Atari.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Quasi-Newton Optimization Methods For Deep Learning Applications
L-BFGS with line search or trust region is applied to deep learning and deep Q-learning, with convergence theorems that rely on strong convexity and mixed empirical results on MNIST and Atari.