OCP-GN is a novel O(d) second-order stochastic optimizer based on optimal control principles that outperforms standard methods on neural network training benchmarks.
Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training[C]//The Twelfth International Conference on Learning Representations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
OCP-GN: A Scalable Second-order Optimizer for Stochastic Optimization
OCP-GN is a novel O(d) second-order stochastic optimizer based on optimal control principles that outperforms standard methods on neural network training benchmarks.