A review of the gumbel-max trick and its extensions for discrete stochasticity in machine learning
IAM Huijben, W Kool, MB Paulus… - IEEE transactions on …, 2022 - ieeexplore.ieee.org
The Gumbel-max trick is a method to draw a sample from a categorical distribution, given by
its unnormalized (log-) probabilities. Over the past years, the machine learning community …
its unnormalized (log-) probabilities. Over the past years, the machine learning community …
Hierarchical sketch induction for paraphrase generation
We propose a generative model of paraphrase generation, that encourages syntactic
diversity by conditioning on an explicit syntactic sketch. We introduce Hierarchical …
diversity by conditioning on an explicit syntactic sketch. We introduce Hierarchical …
Multi-facet clustering variational autoencoders
Work in deep clustering focuses on finding a single partition of data. However, high-
dimensional data, such as images, typically feature multiple interesting characteristics one …
dimensional data, such as images, typically feature multiple interesting characteristics one …
Event representation with sequential, semi-supervised discrete variables
Within the context of event modeling and understanding, we propose a new method for
neural sequence modeling that takes partially-observed sequences of discrete, external …
neural sequence modeling that takes partially-observed sequences of discrete, external …
Relaxed-responsibility hierarchical discrete vaes
Successfully training Variational Autoencoders (VAEs) with a hierarchy of discrete latent
variables remains an area of active research. Vector-Quantised VAEs are a powerful …
variables remains an area of active research. Vector-Quantised VAEs are a powerful …
From Latent Knowledge Gathering to Side Information Injection in Discrete Sequential Models
MMR Taghiabadi - 2024 - search.proquest.com
Abstract Representation learning is crucial for processing sequential and discrete data, such
as text in natural language processing (NLP). From classical methods like topic modeling to …
as text in natural language processing (NLP). From classical methods like topic modeling to …
[PDF][PDF] Fully Unsupervised Image Denoising, Diversity Denoising and Image Segmentation with Limited Annotations
M Prakash - 2022 - core.ac.uk
This thesis marks a gratifying culmination of four years of my PhD research. Although I am
penning down this thesis alone, I feel that there are many individuals all along my PhD …
penning down this thesis alone, I feel that there are many individuals all along my PhD …
Robustness, structure and hierarchy in deep generative models
MJF Willetts - 2021 - ora.ox.ac.uk
Deep learning provides us with ever-more-sophisticated neural networks that can be tuned
via gradient ascent to maximise some objective. Bayesian statistics provides us with a …
via gradient ascent to maximise some objective. Bayesian statistics provides us with a …