AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

On Masked Pre-training and the Marginal Likelihood

Pablo Moreno-Muñoz, Pol G. Recasens, Søren Hauberg

NeurIPS 2023 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Masked autoencoder pretraining · 2 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
Increase the number of random masks from P=1 to P=100 (ablation)Cumulative MPT loss in PPCA · PPCAapproximation to true LML: -60.44 ± 0.47 -> -60.34 ± 0.03; true LML (-60.34)Improved
Increase the number of random masks from P=1 to P=10 (ablation)Cumulative MPT loss in PPCA · PPCAapproximation to true LML: -60.44 ± 0.47 -> -60.22 ± 0.12; true LML (-60.34)Improved
Fix the mask size instead of varying masking rates (ablation)MPT training · PPCAbias of the LML estimateHurt
Use fixed mask size during training (ablation)MPT training · PPCALML maximizationNo clear effect
Train with approximate self-predictive conditional probabilities (ablation)MPT · MNIST and Fashion-MNIST subsetsLMLNo clear effect
Use MPT instead of variational inference with ELBO (ablation)Linear VAE · MNIST and Fashion-MNIST subsetsLMLNo clear effect
Pre-train BERT rather than use random initializationBERT · GLUE AXarea under MPT curve: -5245.31 -> -1715.75Improved
Pre-train BERT rather than use random initializationBERT · GLUE CoLAarea under MPT curve: -5283.52 -> -1657.68Improved
Pre-train BERT rather than use random initializationBERT · GLUE QNLIarea under MPT curve: -5343.98 -> -1770.28Improved
Pre-train BERT rather than use random initializationBERT · GLUE MRPCarea under MPT curve: -5362.21 -> -1773.45Improved

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