Marformer: A Transformer for Predicting Missing Data Distributions
We present the Marformer, a Transformer trained to directly predict conditional marginals given any set of observed values.
ProofPaper ↗
Key points
- Real decisions are made under incomplete information.
- The conditional marginals over the missing variables are the key ingredient for computing Bayes risk and Value of Information (VOI), the expected gain from acquiring one more observation before deciding.
- Like BERT, which is trained to predict missing words from context, the Marformer constructs a hidden-vector representation for each distribution $p(Xi)$ and iteratively refines it through attention to other distributions $p(Xj)$.
- We evaluate across three synthetic domains with missing data---Bayesian networks, discretized multivariate Gaussians, and structured annotation data.
Sources (1)
- [1]Marformer: A Transformer for Predicting Missing Data DistributionsarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 05:33 PM
We present the Marformer, a Transformer trained to directly predict conditional marginals given any set of observed values.
Real decisions are made under incomplete information.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 8, 2026Adapting English Quality Classifiers for Multilingual LLM Pretraining Data Selection
- Oct 8, 2026LEGO: A Lifting-Free Approach for Exocentric-to-Egocentric Video Generation
- Oct 7, 2026MotherTree: Meta-learning on synthetic data improves decision tree training
- Oct 7, 2026Executing Causal Structure Learning with Linear-Attention Transformers
- Oct 7, 2026HuLiGen: Human LiDAR Generation from Parametric Body Models
- Oct 7, 2026Iris-3B: Going Beyond the Latent with Pixel-Space Diffusion Training, Conversion and Fine-Tuning