Diffusion models have been successful on a range of conditional generati...
Classical results establish that ensembles of small models benefit when
...
Likelihood-based deep generative models have recently been shown to exhi...
Gaussian processes scale prohibitively with the size of the dataset. In
...
Data augmentation plays a key role in modern machine learning pipelines....
Probability distributions supported on the simplex enjoy a wide range of...
Ensembling neural networks is an effective way to increase accuracy, and...
Interstellar dust corrupts nearly every stellar observation, and account...
Deep discrete structured models have seen considerable progress recently...
Bayesian model criticism is an important part of the practice of Bayesia...
Gaussian processes remain popular as a flexible and expressive model cla...
Large width limits have been a recent focus of deep learning research: m...
Normalizing flows are invertible neural networks with tractable
change-o...
Integrating methods for time-to-event prediction with diagnostic imaging...
Advances in computing power, deep learning architectures, and expert lab...
Non-invasive and cost effective in nature, the echocardiogram allows for...
Scalable Gaussian Process methods are computationally attractive, yet
in...
Modern deep learning is primarily an experimental science, in which empi...
Gaussian Processes (GPs) provide a powerful probabilistic framework for
...
Simplex-valued data appear throughout statistics and machine learning, f...
Paraphrase generation is a longstanding important problem in natural lan...
The Gumbel-Softmax is a continuous distribution over the simplex that is...
Variational autoencoders (VAE) have quickly become a central tool in mac...
Recently much attention has been paid to deep generative models, since t...
Gaussian processes are the leading class of distributions on random
func...
An electrocardiogram (EKG) is a common, non-invasive test that measures ...
The wide adoption of Convolutional Neural Networks (CNNs) in application...
Estimation of reliable whole-brain connectivity is a crucial step toward...
Many matching, tracking, sorting, and ranking problems require probabili...
Maximum entropy modeling is a flexible and popular framework for formula...
A body of recent work in modeling neural activity focuses on recovering
...
Kernel methods are one of the mainstays of machine learning, but the pro...
The computational and storage complexity of kernel machines presents the...
Neuroprosthetic brain-computer interfaces function via an algorithm whic...
A common approach for Bayesian computation with big data is to partition...
Exact Gaussian Process (GP) regression has O(N^3) runtime for data size ...
While Gaussian probability densities are omnipresent in applied mathemat...