Search Results for author:
Found 11 papers, 5 papers with code
Mixed Variational Flows for Discrete Variables
First, we develop a measure-preserving and discrete (MAD) invertible map that leaves the discrete target invariant, and then create a mixed variational flow (MAD Mix) based on that map.
Non-parametric Hypothesis Tests for Distributional Group Symmetry
Finally, we apply them to testing for symmetry in geomagnetic satellite data and in two problems from high-energy particle physics.
Indeterminacy in Generative Models: Characterization and Strong Identifiability
Most modern probabilistic generative models, such as the variational autoencoder (VAE), have certain indeterminacies that are unresolvable even with an infinite amount of data.
Beauty in Machine Learning: Purpose and Enlightenment
Drawing on empirical research and theories of beauty from psychology, and on philosophical investigations into the role of beauty in scientific research, I argue that aesthetic considerations are valuable to machine research in two modes.
Lossy Compression for Lossless Prediction
Most data is automatically collected and only ever "seen" by algorithms.
Ranked #1 on
Image Compression
on Oxford-IIIT Pet Dataset
(using extra training data)
Uncertainty in Neural Processes
We aim this work to be a counterpoint to a recent trend in the literature that stresses achieving good samples when the amount of conditioning data is large.
On the Benefits of Invariance in Neural Networks
Many real world data analysis problems exhibit invariant structure, and models that take advantage of this structure have shown impressive empirical performance, particularly in deep learning.
Probabilistic symmetries and invariant neural networks
Treating neural network inputs and outputs as random variables, we characterize the structure of neural networks that can be used to model data that are invariant or equivariant under the action of a compact group.
Sequential sampling of Gaussian process latent variable models
We consider the problem of inferring a latent function in a probabilistic model of data.
Sampling and Inference for Beta Neutral-to-the-Left Models of Sparse Networks
Empirical evidence suggests that heavy-tailed degree distributions occurring in many real networks are well-approximated by power laws with exponents $\eta$ that may take values either less than and greater than two.
Random Walk Models of Network Formation and Sequential Monte Carlo Methods for Graphs
We introduce a class of generative network models that insert edges by connecting the starting and terminal vertices of a random walk on the network graph.
