ML: Autoencoder

Machine-learning ideas tagged Autoencoder in the ML taxonomy of the Math2NN corpus.

2 ideas found

ML: Autoencoder Math: Control theory Clear all

✗ Mechanism failed 2026

Conley-Certified Latent World Model

Train an encoder-decoder world model together with a latent transition map, but certify latent attractors only when the learned model is approximately semiconjugate to the observed high-dimensional dynamics with residual below the isolating-set margin. Compute a Conley-Morse graph on a latent grid and lift each certified recurrent component through the decoder to obtain a region in the original state space where an attractor or invariant set is predicted to exist.

Useful8/10

Difficulty7/10

Novelty8/10

Theory Stability Accuracy Generalization

Paper: Characterizing High-dimensional Dynamics by Combinatorial-Topological Methods on a Latent Space arXiv:2609.01509

✗ Failed on benchmark 2026

Quadratic center-manifold bottleneck

Replace a conventional linear decoder in an autoencoder or latent state-space model with an explicit quadratic manifold decoder, allowing a small latent vector to represent curved and transport-like state trajectories. Add a dynamics-aware invariance loss that penalizes the discrepancy between the time derivative of the quadratic manifold and the neural dynamics evaluated on that manifold.

Useful7/10

Difficulty5/10

Novelty6/10

Architecture Accuracy Memory Sample efficiency

Paper: Beyond linear subspaces: Nonlinear moment matching meets quadratic manifolds arXiv:2608.19486