Browsing Theses by Supervisor "Yu, Yaoliang"
Now showing items 1-9 of 9
-
Accelerating and Privatizing Diffusion Models
(University of Waterloo, 2023-08-17)Diffusion models (DMs) have emerged as a powerful class of generative models. DMs offer both state-of-the-art synthesis quality and sample diversity in combination with a robust and scalable learning objective. DMs rely ... -
A Convergent Hierarchy of Certificates for Constrained Signomial Positivity
(University of Waterloo, 2020-09-24)Optimization is at the heart of many engineering problems. Many optimization problems, however, are computationally intractable. One approach to tackle such intractability is to find a tractable problem whose solution, ... -
Efficient Inference of Transformers in Natural Language Processing: Early Exiting and Beyond
(University of Waterloo, 2023-01-24)Large-scale pre-trained transformer models such as BERT have become ubiquitous in Natural Language Processing (NLP) research and applications. They bring significant improvements to both academia benchmarking tasks and ... -
Likelihood-based Density Estimation using Deep Architectures
(University of Waterloo, 2019-12-20)Multivariate density estimation is a central problem in unsupervised machine learning that has been studied immensely in both statistics and machine learning. Several methods have thus been proposed for density estimation ... -
MT-MAG: Accurate and interpretable machine learning for complete or partial taxonomic assignments of metagenome-assembled genomes
(University of Waterloo, 2022-05-19)We propose MT-MAG, a novel machine learning-based software tool for the complete or partial hierarchically-structured taxonomic classification of metagenome-assembled genomes (MAGs). MT-MAG is capable of classifying large ... -
Multivariate Triangular Quantile Maps for Novelty Detection
(University of Waterloo, 2024-05-21)Novelty detection, a fundamental task in the field of machine learning, has drawn a lot of recent attention due to its wide-ranging applications and the rise of neural approaches. In this thesis, we present a general ... -
Understanding Minimax Optimization in Modern Machine Learning
(University of Waterloo, 2021-07-21)Recent years has seen a surge of interest in building learning machines through adversarial training. One type of adversarial training is through a discriminator or an auxiliary classifier, such as Generative Adversarial ... -
Unsupervised Multilingual Alignment using Wasserstein Barycenter
(University of Waterloo, 2020-01-23)We investigate the language alignment problem when there are multiple languages, and we are interested in finding translation between all pairs of languages. The problem of language alignment has long been an exciting topic ... -
Wasserstein Adversarial Robustness
(University of Waterloo, 2020-09-21)Deep models, while being extremely flexible and accurate, are surprisingly vulnerable to ``small, imperceptible'' perturbations known as adversarial attacks. While the majority of existing attacks focus on measuring ...