Autoencoders as continuous-time optimal control problems solved with rank-adaptive tensor compression, yielding memory savings and automatic layer-width profiles on MNIST denoising and deblurring.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
OCTANE -- Optimal Control for Tensor-based Autoencoder Network Emergence: Explicit Case
Autoencoders as continuous-time optimal control problems solved with rank-adaptive tensor compression, yielding memory savings and automatic layer-width profiles on MNIST denoising and deblurring.