Search Results for author:
Found 7 papers, 4 papers with code
Polynomial Semantics of Tractable Probabilistic Circuits
Probabilistic circuits compute multilinear polynomials that represent multivariate probability distributions.
Tractable Control for Autoregressive Language Generation
To overcome this challenge, we propose to use tractable probabilistic models (TPMs) to impose lexical constraints in autoregressive text generation models, which we refer to as GeLaTo (Generating Language with Tractable Constraints).
Mixtures of All Trees
We show that it is possible to parameterize this Mixture of All Trees (MoAT) model compactly (using a polynomial-size representation) in a way that allows for tractable likelihood computation and optimization via stochastic gradient descent.
Scaling Up Probabilistic Circuits by Latent Variable Distillation
We propose to overcome such bottleneck by latent variable distillation: we leverage the less tractable but more expressive deep generative models to provide extra supervision over the latent variables of PCs.
On the Paradox of Learning to Reason from Data
Logical reasoning is needed in a wide range of NLP tasks.
Probabilistic Generating Circuits
Generating functions, which are widely used in combinatorics and probability theory, encode function values into the coefficients of a polynomial.
On the Relationship Between Probabilistic Circuits and Determinantal Point Processes
Central to this effort is the development of tractable probabilistic models (TPMs): models whose structure guarantees efficient probabilistic inference algorithms.
