conftrace_

power divergence

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

student's t distribution (1) rare word prediction (1) neural network (1) heavy-tailed data (1) word frequency (1) neural language model (1) noise contrastive estimation (1) language model (1) variational autoencoder (1) latent representation (1)

Papers

t^3-Variational Autoencoder: Learning Heavy-tailed Data with Student's t and Power Divergence ICLR 2024 Experimenting with Power Divergences for Language Modeling EMNLP 2019