
-
Image Completion via Inference in Deep Generative Models
We consider image completion from the perspective of amortized inference...
read it
-
Robust Asymmetric Learning in POMDPs
Policies for partially observed Markov decision processes can be efficie...
read it
-
Annealed Importance Sampling with q-Paths
Annealed importance sampling (AIS) is the gold standard for estimating p...
read it
-
Ensemble Squared: A Meta AutoML System
The continuing rise in the number of problems amenable to machine learni...
read it
-
Gaussian Process Bandit Optimization of the Thermodynamic Variational Objective
Achieving the full promise of the Thermodynamic Variational Objective (T...
read it
-
Uncertainty in Neural Processes
We explore the effects of architecture and training objective choice on ...
read it
-
Assisting the Adversary to Improve GAN Training
We propose a method for improved training of generative adversarial netw...
read it
-
All in the Exponential Family: Bregman Duality in Thermodynamic Variational Inference
The recently proposed Thermodynamic Variational Objective (TVO) leverage...
read it
-
Semi-supervised Sequential Generative Models
We introduce a novel objective for training deep generative time-series ...
read it
-
Improving Few-Shot Visual Classification with Unlabelled Examples
We propose a transductive meta-learning method that uses unlabelled inst...
read it
-
Planning as Inference in Epidemiological Models
In this work we demonstrate how existing software tools can be used to a...
read it
-
Coping With Simulators That Don't Always Return
Deterministic models are approximations of reality that are easy to inte...
read it
-
Improved Few-Shot Visual Classification
Few-shot learning is a fundamental task in computer vision that carries ...
read it
-
Attention for Inference Compilation
We present a new approach to automatic amortized inference in universal ...
read it
-
Deep Probabilistic Surrogate Networks for Universal Simulator Approximation
We present a framework for automatically structuring and training fast, ...
read it
-
Amortized Rejection Sampling in Universal Probabilistic Programming
Existing approaches to amortized inference in probabilistic programs wit...
read it
-
Safer End-to-End Autonomous Driving via Conditional Imitation Learning and Command Augmentation
Imitation learning is a promising approach to end-to-end training of aut...
read it
-
The Virtual Patch Clamp: Imputing C. elegans Membrane Potentials from Calcium Imaging
We develop a stochastic whole-brain and body simulator of the nematode r...
read it
-
Amortized Monte Carlo Integration
Current approaches to amortizing Bayesian inference focus solely on appr...
read it
-
Etalumis: Bringing Probabilistic Programming to Scientific Simulators at Scale
Probabilistic programming languages (PPLs) are receiving widespread atte...
read it
-
The Thermodynamic Variational Objective
We introduce the thermodynamic variational objective (TVO) for learning ...
read it
-
Near-Optimal Glimpse Sequences for Improved Hard Attention Neural Network Training
We introduce the use of Bayesian optimal experimental design techniques ...
read it
-
Imitation Learning of Factored Multi-agent Reactive Models
We apply recent advances in deep generative modeling to the task of imit...
read it
-
LF-PPL: A Low-Level First Order Probabilistic Programming Language for Non-Differentiable Models
We develop a new Low-level, First-order Probabilistic Programming Langua...
read it
-
An Introduction to Probabilistic Programming
This document is designed to be a first-year graduate-level introduction...
read it
-
Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model
We present a novel framework that enables efficient probabilistic infere...
read it
-
Inference Trees: Adaptive Inference with Exploration
We introduce inference trees (ITs), a new class of inference methods tha...
read it
-
Deep Variational Reinforcement Learning for POMDPs
Many real-world sequential decision making problems are partially observ...
read it
-
Revisiting Reweighted Wake-Sleep
Discrete latent-variable models, while applicable in a variety of settin...
read it
-
Discontinuous Hamiltonian Monte Carlo for Probabilistic Programs
Hamiltonian Monte Carlo (HMC) is the dominant statistical inference algo...
read it
-
High Throughput Synchronous Distributed Stochastic Gradient Descent
We introduce a new, high-throughput, synchronous, distributed, data-para...
read it
-
Tighter Variational Bounds are Not Necessarily Better
We provide theoretical and empirical evidence that using tighter evidenc...
read it
-
Improvements to Inference Compilation for Probabilistic Programming in Large-Scale Scientific Simulators
We consider the problem of Bayesian inference in the family of probabili...
read it
-
Faithful Model Inversion Substantially Improves Auto-encoding Variational Inference
In learning deep generative models, the encoder for variational inferenc...
read it
-
Updating the VESICLE-CNN Synapse Detector
We present an updated version of the VESICLE-CNN algorithm presented by ...
read it
-
On the Opportunities and Pitfalls of Nesting Monte Carlo Estimators
We present a formalization of nested Monte Carlo (NMC) estimation, where...
read it
-
Bayesian Optimization for Probabilistic Programs
We present the first general purpose framework for marginal maximum a po...
read it
-
Learning Disentangled Representations with Semi-Supervised Deep Generative Models
Variational autoencoders (VAEs) learn representations of data by jointly...
read it
-
Auto-Encoding Sequential Monte Carlo
We introduce AESMC: a method for using deep neural networks for simultan...
read it
-
Online Learning Rate Adaptation with Hypergradient Descent
We introduce a general method for improving the convergence rate of grad...
read it
-
Using Synthetic Data to Train Neural Networks is Model-Based Reasoning
We draw a formal connection between using synthetic training data to opt...
read it
-
Inducing Interpretable Representations with Variational Autoencoders
We develop a framework for incorporating structured graphical models in ...
read it
-
Probabilistic structure discovery in time series data
Existing methods for structure discovery in time series data construct i...
read it
-
Inference Compilation and Universal Probabilistic Programming
We introduce a method for using deep neural networks to amortize the cos...
read it
-
Spreadsheet Probabilistic Programming
Spreadsheet workbook contents are simple programs. Because of this, prob...
read it
-
Inference Networks for Sequential Monte Carlo in Graphical Models
We introduce a new approach for amortizing inference in directed graphic...
read it
-
Interacting Particle Markov Chain Monte Carlo
We introduce interacting particle Markov chain Monte Carlo (iPMCMC), a P...
read it
-
Semantics for probabilistic programming: higher-order functions, continuous distributions, and soft constraints
We study the semantic foundation of expressive probabilistic programming...
read it
-
Data-driven Sequential Monte Carlo in Probabilistic Programming
Most of Markov Chain Monte Carlo (MCMC) and sequential Monte Carlo (SMC)...
read it
-
A New Approach to Probabilistic Programming Inference
We introduce and demonstrate a new approach to inference in expressive p...
read it