Discrete Latent Variable Model
A model that assumes observed data are generated by discrete categories (latent states) that cannot be observed directly. Shared latent states capture the dependency structure among observations, playing a role similar to latent variables in mixture models and topic models.
Timeline (last 90 days)
TAPES pretrains with a joint likelihood parameterized by shared discrete latent variables to explicitly model the conditional co-occurrence relationships among prediction targets.
In TAPES's discrete latent variable model, given the value of the latent variable, the prediction targets are conditionally independent; after marginalizing out the latent variable, a conditional co-occurrence structure emerges among the targets.
All Facts (2)
TAPES pretrains with a joint likelihood parameterized by shared discrete latent variables to explicitly model the conditional co-occurrence relationships among prediction targets.
50%UnverifiedIn TAPES's discrete latent variable model, given the value of the latent variable, the prediction targets are conditionally independent; after marginalizing out the latent variable, a conditional co-occurrence structure emerges among the targets.
50%