AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Connections with Robust PCA and the Role of Emergent Sparsity in Variational Autoencoder Models

Bin Dai, Yu Wang, John Aston, Gang Hua, David Wipf

JMLR 2018 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Regularizing VAE latent information · 43 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add a stochastic encoder covariance (VAE instead of deterministic AE-l2) (ablation)autoencoder on corrupted nonlinear manifold data · Synthetic manifold recovery with outliersnormalized MSEImproved
use VAE instead of AE-l1 sparse latent penalty (ablation)autoencoder on corrupted nonlinear manifold data · Synthetic manifold recovery with outliersnormalized MSEImproved
use VAE instead of convex RPCAmanifold recovery with outliers · Synthetic manifold recovery with outliersnormalized MSEImproved
add decoder hidden layers (Nd from 0 to 1) (ablation)VAE with Ne=0 · Synthetic manifold, true latent dim 20nonzero columns in W1: 30.0 -> 21.1Improved
add decoder hidden layers (Nd from 0 to 3) (ablation)VAE with Ne=3 · Synthetic manifold, true latent dim 20nonzero columns in W1: 30.0 -> 20.0Improved
add decoder hidden layers (Nd from 0 to 2) (ablation)VAE with Ne=2 · Synthetic manifold, true latent dim 20nonzero columns in W1: 30.0 -> 20.0Improved
add encoder hidden layers (Ne from 0 to 3) at Nd=1 (ablation)VAE · Synthetic manifold, true latent dim 20nonzero columns in W1: 21.1 -> 20.4Improved
use a VAE instead of an AE for latent dimension pruning on MNIST (ablation)MNIST VAE with kappa above 15 · MNISTnonzero columns in W1Improved
use tuned C2 = 10^3 for AE-l2 instead of default C2 = 1 (ablation)AE-l2 · Synthetic manifold recovery with outliersnormalized MSE: C2 = 1 -> C2 = 10^3Improved
use 5 latent samples instead of 1 per input (ablation)VAE · MNIST with outliers (appendix)normalized MSE: tau = 1 -> tau = 5Improved
use VAE instead of convex RPCAMNIST denoising · MNIST with outliers (appendix)normalized MSEImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy