CRONOS introduces scalable convex optimization for two-layer neural networks reaching ImageNet scale, with CRONOS-AM extending to arbitrary multi-layer architectures while matching tuned deep learning performance.
Newton sketch: A near linear-time optimization algorithm with linear-quadratic convergence
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CRONOS: Enhancing Deep Learning with Scalable GPU Accelerated Convex Neural Networks
CRONOS introduces scalable convex optimization for two-layer neural networks reaching ImageNet scale, with CRONOS-AM extending to arbitrary multi-layer architectures while matching tuned deep learning performance.