MEDAL distills manifold embeddings into autoencoders to enable out-of-sample extension and held-out validation of dimension reduction methods.
hub
Neural networks and principal component analysis: Learning from examples without local minima.Neural Networks, 2(1):53–58
3 Pith papers cite this work, alongside 1,402 external citations. Polarity classification is still indexing.
3
Pith papers citing it
1,402
external citations · OpenAlex
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Deep sequence models develop geometric memory in embeddings that encodes novel global relationships, transforming l-fold composition tasks into 1-step navigation via a natural spectral bias connected to Node2Vec.
Optimal depth-wise learning-rate scaling in deep scalar linear networks is data-dependent, so data-agnostic rules fail to transfer while the data-aware rule yields depth-independent linear convergence.
citing papers explorer
-
MEDAL: Manifold Embedding Distillation via Autoencoder Learning
MEDAL distills manifold embeddings into autoencoders to enable out-of-sample extension and held-out validation of dimension reduction methods.
-
Deep sequence models tend to memorize geometrically; it is unclear why
Deep sequence models develop geometric memory in embeddings that encodes novel global relationships, transforming l-fold composition tasks into 1-step navigation via a natural spectral bias connected to Node2Vec.
-
Optimal Learning Rate Scaling Depends on Data in Deep Scalar Linear Networks
Optimal depth-wise learning-rate scaling in deep scalar linear networks is data-dependent, so data-agnostic rules fail to transfer while the data-aware rule yields depth-independent linear convergence.