
What Are Bayesian Neural Network Posteriors Really Like?
The posterior over Bayesian neural network (BNN) parameters is extremely...
read it

Underspecification Presents Challenges for Credibility in Modern Machine Learning
ML models often exhibit unexpectedly poor behavior when they are deploye...
read it

tfp.mcmc: Modern Markov Chain Monte Carlo Tools Built for Modern Hardware
Markov chain Monte Carlo (MCMC) is widely regarded as one of the most im...
read it

Hamiltonian Monte Carlo Swindles
Hamiltonian Monte Carlo (HMC) is a powerful Markov chain Monte Carlo (MC...
read it

Automatically Batching ControlIntensive Programs for Modern Accelerators
We present a general approach to batching arbitrary computations for acc...
read it

Automatic Reparameterisation of Probabilistic Programs
Probabilistic programming has emerged as a powerful paradigm in statisti...
read it

Autoconj: Recognizing and Exploiting Conjugacy Without a DomainSpecific Language
Deriving conditional and marginal distributions using conjugacy relation...
read it

The LORACs prior for VAEs: Letting the Trees Speak for the Data
In variational autoencoders, the prior on the latent codes z is often tr...
read it

An Improved Relative SelfAttention Mechanism for Transformer with Application to Music Generation
Music relies heavily on selfreference to build structure and meaning. W...
read it

Music Transformer
Music relies heavily on repetition to build structure and meaning. Self...
read it

Variational Autoencoders for Collaborative Filtering
We extend variational autoencoders (VAEs) to collaborative filtering for...
read it

Generalizing Hamiltonian Monte Carlo with Neural Networks
We present a generalpurpose method to train Markov chain Monte Carlo ke...
read it

Multimodal Prediction and Personalization of Photo Edits with Deep Generative Models
Professionalgrade software applications are powerful but complicatedex...
read it

Stochastic Gradient Descent as Approximate Bayesian Inference
Stochastic Gradient Descent with a constant learning rate (constant SGD)...
read it

Deep Probabilistic Programming
We propose Edward, a Turingcomplete probabilistic programming language....
read it

A Variational Analysis of Stochastic Gradient Algorithms
Stochastic Gradient Descent (SGD) is an important algorithm in machine l...
read it

The Stan Math Library: ReverseMode Automatic Differentiation in C++
As computational challenges in optimization and statistical inference gr...
read it

A trustregion method for stochastic variational inference with applications to streaming data
Stochastic variational inference allows for fast posterior inference in ...
read it

Image Classification and Retrieval from UserSupplied Tags
This paper proposes direct learning of image classification from usersu...
read it

Beta Process Nonnegative Matrix Factorization with Stochastic Structured MeanField Variational Inference
Beta process is the standard nonparametric Bayesian prior for latent fac...
read it

Structured Stochastic Variational Inference
Stochastic variational inference makes it possible to approximate poster...
read it

A Generative ProductofFilters Model of Audio
We propose the productoffilters (PoF) model, a generative model that d...
read it
Matthew D. Hoffman
is this you? claim profile
Senior Research Scientist at Googlesince 2016, Senior Research Scientist at Adobe from 20122016, research scientist in the Creative Technologies Laboratory at Adobe from 20122016, Postdoc in the Statistics Department at Columbia University, Ph.D. at Princeton University in Computer Science 20042010.