Search Results for author:
Found 48 papers, 22 papers with code
Pathologies of Predictive Diversity in Deep Ensembles
Here we demonstrate that these intuitions do not apply to high-capacity neural network ensembles (deep ensembles), and in fact the opposite is often true.
Posterior Collapse and Latent Variable Non-identifiability
Unfortunately, variational autoencoders often suffer from posterior collapse: the posterior of the latent variables is equal to its prior, rendering the variational autoencoder useless as a means to produce meaningful representations.
Denoising Deep Generative Models
Likelihood-based deep generative models have recently been shown to exhibit pathological behaviour under the manifold hypothesis as a consequence of using high-dimensional densities to model data with low-dimensional structure.
Posterior and Computational Uncertainty in Gaussian Processes
For any method in this class, we prove (i) convergence of its posterior mean in the associated RKHS, (ii) decomposability of its combined posterior covariance into mathematical and computational covariances, and (iii) that the combined variance is a tight worst-case bound for the squared error between the method's posterior mean and the latent function.
Data Augmentation for Compositional Data: Advancing Predictive Models of the Microbiome
Our work extends the success of data augmentation to compositional data, i. e., simplex-valued data, which is of particular interest in the context of the human microbiome.
On the Normalizing Constant of the Continuous Categorical Distribution
This family enjoys remarkable mathematical simplicity; its density function resembles that of the Dirichlet distribution, but with a normalizing constant that can be written in closed form using elementary functions only.
Deep Ensembles Work, But Are They Necessary?
While deep ensembles are a practical way to achieve improvements to predictive power, uncertainty quantification, and robustness, our results show that these improvements can be replicated by a (larger) single model.
Scaling Structured Inference with Randomization
Here, we propose a family of randomized dynamic programming (RDP) algorithms for scaling structured models to tens of thousands of latent states.
Preconditioning for Scalable Gaussian Process Hyperparameter Optimization
While preconditioning is well understood in the context of CG, we demonstrate that it can also accelerate convergence and reduce variance of the estimates for the log-determinant and its derivative.
The Limitations of Large Width in Neural Networks: A Deep Gaussian Process Perspective
Our analysis in this paper decouples capacity and width via the generalization of neural networks to Deep Gaussian Processes (Deep GP), a class of nonparametric hierarchical models that subsume neural nets.
Rectangular Flows for Manifold Learning
Normalizing flows are invertible neural networks with tractable change-of-volume terms, which allow optimization of their parameters to be efficiently performed via maximum likelihood.
Simulating time to event prediction with spatiotemporal echocardiography deep learning
Integrating methods for time-to-event prediction with diagnostic imaging modalities is of considerable interest, as accurate estimates of survival requires accounting for censoring of individuals within the observation period.
Medical Imaging and Machine Learning
Advances in computing power, deep learning architectures, and expert labelled datasets have spurred the development of medical imaging artificial intelligence systems that rival clinical experts in a variety of scenarios.
Predicting post-operative right ventricular failure using video-based deep learning
Non-invasive and cost effective in nature, the echocardiogram allows for a comprehensive assessment of the cardiac musculature and valves.
Bias-Free Scalable Gaussian Processes via Randomized Truncations
In the case of RFF, we show that the bias-to-variance conversion is indeed a trade-off: the additional variance proves detrimental to optimization.
Deep Graph Pose: a semi-supervised deep graphical model for improved animal pose tracking
Noninvasive behavioral tracking of animals is crucial for many scientific investigations.
Recurrent Switching Dynamical Systems Models for Multiple Interacting Neural Populations
We allow the nature of these interactions to change over time by using a discrete set of dynamical states.
Uses and Abuses of the Cross-Entropy Loss: Case Studies in Modern Deep Learning
Modern deep learning is primarily an experimental science, in which empirical advances occasionally come at the expense of probabilistic rigor.
Linear-time inference for Gaussian Processes on one dimension
Gaussian Processes (GPs) provide powerful probabilistic frameworks for interpolation, forecasting, and smoothing, but have been hampered by computational scaling issues.
The continuous categorical: a novel simplex-valued exponential family
Simplex-valued data appear throughout statistics and machine learning, for example in the context of transfer learning and compression of deep networks.
Paraphrase Generation with Latent Bag of Words
Inspired by variational autoencoders with discrete latent structures, in this work, we propose a latent bag of words (BOW) model for paraphrase generation.
Invertible Gaussian Reparameterization: Revisiting the Gumbel-Softmax
The Gumbel-Softmax is a continuous distribution over the simplex that is often used as a relaxation of discrete distributions.
BehaveNet: nonlinear embedding and Bayesian neural decoding of behavioral videos
Here we introduce a probabilistic framework for the analysis of behavioral video and neural activity.
The continuous Bernoulli: fixing a pervasive error in variational autoencoders
Variational autoencoders (VAE) have quickly become a central tool in machine learning, applicable to a broad range of data types and latent variable models.
Deep Random Splines for Point Process Intensity Estimation
Gaussian processes are the leading class of distributions on random functions, but they suffer from well known issues including difficulty scaling and inflexibility with respect to certain shape constraints (such as nonnegativity).
Approximating exponential family models (not single distributions) with a two-network architecture
Recently much attention has been paid to deep generative models, since they have been used to great success for variational inference, generation of complex data types, and more.
Deep Random Splines for Point Process Intensity Estimation of Neural Population Data
Gaussian processes are the leading class of distributions on random functions, but they suffer from well known issues including difficulty scaling and inflexibility with respect to certain shape constraints (such as nonnegativity).
A Probabilistic Model of Cardiac Physiology and Electrocardiograms
An electrocardiogram (EKG) is a common, non-invasive test that measures the electrical activity of a patient's heart.
Calibrating Deep Convolutional Gaussian Processes
The wide adoption of Convolutional Neural Networks (CNNs) in applications where decision-making under uncertainty is fundamental, has brought a great deal of attention to the ability of these models to accurately quantify the uncertainty in their predictions.
Bayesian estimation for large scale multivariate Ornstein-Uhlenbeck model of brain connectivity
Estimation of reliable whole-brain connectivity is a crucial step towards the use of connectivity information in quantitative approaches to the study of neuropsychiatric disorders.
Reparameterizing the Birkhoff Polytope for Variational Permutation Inference
Many matching, tracking, sorting, and ranking problems require probabilistic reasoning about possible permutations, a set that grows factorially with dimension.
Maximum Entropy Flow Networks
Maximum entropy modeling is a flexible and popular framework for formulating statistical models given partial knowledge.
Linear dynamical neural population models through nonlinear embeddings
A body of recent work in modeling neural activity focuses on recovering low-dimensional latent features that capture the statistical structure of large-scale neural populations.
Bayesian Learning of Kernel Embeddings
The posterior mean of our model is closely related to recently proposed shrinkage estimators for kernel mean embeddings, while the posterior uncertainty is a new, interesting feature with various possible applications.
High-dimensional neural spike train analysis with generalized count linear dynamical systems
Latent factor models have been widely used to analyze simultaneous recordings of spike trains from large, heterogeneous neural populations.
Bayesian Active Model Selection with an Application to Automated Audiometry
Using this and a previously published model for healthy responses, the proposed method is shown to be capable of diagnosing the presence or absence of NIHL with drastically fewer samples than existing approaches.
Neuroprosthetic decoder training as imitation learning
We describe how training a decoder in this way is a novel variant of an imitation learning problem, where an oracle or expert is employed for supervised training in lieu of direct observations, which are not available.
Sparse Probit Linear Mixed Model
Formulated as models for linear regression, LMMs have been restricted to continuous phenotypes.
Expectation propagation as a way of life: A framework for Bayesian inference on partitioned data
A common divide-and-conquer approach for Bayesian computation with big data is to partition the data, perform local inference for each piece separately, and combine the results to obtain a global posterior approximation.
Fast Kernel Learning for Multidimensional Pattern Extrapolation
This difficulty is compounded by the fact that Gaussian processes are typically only tractable for small datasets, and scaling an expressive kernel learning approach poses different challenges than scaling a standard Gaussian process model.
Clustered factor analysis of multineuronal spike data
High-dimensional, simultaneous recordings of neural spiking activity are often explored, analyzed and visualized with the help of latent variable or factor models.
Linear Dimensionality Reduction: Survey, Insights, and Generalizations
Modern techniques for optimization over matrix manifolds enable a generic linear dimensionality reduction solver, which accepts as input data and an objective to be optimized, and returns, as output, an optimal low-dimensional projection of the data.
GPatt: Fast Multidimensional Pattern Extrapolation with Gaussian Processes
We introduce a new Bayesian nonparametric framework -- GPatt -- enabling automatic pattern extrapolation with Gaussian processes on large multidimensional datasets.
Empirical models of spiking in neural populations
Neurons in the neocortex code and compute as part of a locally interconnected population.
Dynamical segmentation of single trials from population neural data
Simultaneous recordings of many neurons embedded within a recurrently-connected cortical network may provide concurrent views into the dynamical processes of that network, and thus its computational function.
Gaussian Probabilities and Expectation Propagation
We consider these unexpected results empirically and theoretically, both for the problem of Gaussian probabilities and for EP more generally.
Gaussian-process factor analysis for low-dimensional single-trial analysis of neural population activity
We applied these methods to the activity of 61 neurons recorded simultaneously in macaque premotor and motor cortices during reach planning and execution.
