Matthew Willetts
7 papers · 2020–2022 · 2 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(17)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Deep Learning
(6)
Machine Learning
(5)
Models
(5)
Architectures
(3)
Core Methods
(3)
Optimization & Theory · Machine Learning
(3)
Artificial Intelligence
(2)
Computer Science
(1)
Applications
(1)
Core AI
(1)
Learning Paradigms
(1)
Learning Types · Deep Learning
(1)
Learning Types · Machine Learning
(1)
Optimization & Theory · Deep Learning
(1)
Keywords
variational autoencoder
(5)
adversarial robustness
(3)
unsupervised learning
(2)
kl divergence
(1)
u-net architecture
(1)
diffusion process
(1)
wavelet basis
(1)
generative model
(1)
probabilistic model
(1)
latent representation
(1)
latent variable
(1)
disentangled representation
(1)
lipschitz constant
(1)
fourier domain
(1)
multi-resolution analysis
(1)
robust training
(1)
calibrated classifier
(1)
feature disentangling
(1)
input perturbation
(1)
gaussian noise injection
(1)
Papers
A Multi-Resolution Framework for U-Nets with Applications to Hierarchical VAEs
NeurIPS 2022
Certifiably Robust Variational Autoencoders
AISTATS 2022
Variational Autoencoders: A Harmonic Perspective
AISTATS 2022
Learning Bijective Feature Maps for Linear ICA
AISTATS 2021
Multi-Facet Clustering Variational Autoencoders
NeurIPS 2021
Towards a Theoretical Understanding of the Robustness of Variational Autoencoders
AISTATS 2021
Explicit Regularisation in Gaussian Noise Injections
NeurIPS 2020