140 citations · 735 across the 46 of their papers we have counts for
17 papers · 1 filter
Annealed Importance Sampling with q-Paths
Rob Brekelmans, Vaden Masrani, Thang Bui +4
Annealed importance sampling (AIS) is the gold standard for estimating partition functions or marginal likelihoods, corresponding to importance sampling over a path of distribution…
Robust Asymmetric Learning in POMDPs
Andrew Warrington, J. Wilder Lavington, Adam Ścibior +2
Policies for partially observed Markov decision processes can be efficiently learned by imitating policies for the corresponding fully observed Markov decision processes. Unfortuna…
Ensemble Squared: A Meta AutoML System
Jason Yoo, Tony Joseph, Dylan Yung +2
There are currently many barriers that prevent non-experts from exploiting machine learning solutions ranging from the lack of intuition on statistical learning techniques to the t…
Gaussian Process Bandit Optimization of the Thermodynamic Variational Objective
Vu Nguyen, Vaden Masrani, Rob Brekelmans +2
Achieving the full promise of the Thermodynamic Variational Objective (TVO), a recently proposed variational lower bound on the log evidence involving a one-dimensional Riemann int…
Uncertainty in Neural Processes
Saeid Naderiparizi, Kenny Chiu, Benjamin Bloem-Reddy +1
We explore the effects of architecture and training objective choice on amortized posterior predictive inference in probabilistic conditional generative models. We aim this work to…
Assisting the Adversary to Improve GAN Training
Andreas Munk, William Harvey, Frank Wood
Some of the most popular methods for improving the stability and performance of GANs involve constraining or regularizing the discriminator. In this paper we consider a largely ove…
All in the Exponential Family: Bregman Duality in Thermodynamic Variational Inference
Rob Brekelmans, Vaden Masrani, Frank Wood +2
The recently proposed Thermodynamic Variational Objective (TVO) leverages thermodynamic integration to provide a family of variational inference objectives, which both tighten and…
Semi-supervised Sequential Generative Models
Michael Teng, Tuan Anh Le, Adam Scibior +1
We introduce a novel objective for training deep generative time-series models with discrete latent variables for which supervision is only sparsely available. This instance of sem…
Coping With Simulators That Don't Always Return
Andrew Warrington, Saeid Naderiparizi, Frank Wood
Deterministic models are approximations of reality that are easy to interpret and often easier to build than stochastic alternatives. Unfortunately, as nature is capricious, observ…
Attention for Inference Compilation
William Harvey, Andreas Munk, Atılım Güneş Baydin +2
We present a new approach to automatic amortized inference in universal probabilistic programs which improves performance compared to current methods. Our approach is a variation o…
Amortized Rejection Sampling in Universal Probabilistic Programming
Saeid Naderiparizi, Adam Ścibior, Andreas Munk +9
Naive approaches to amortized inference in probabilistic programs with unbounded loops can produce estimators with infinite variance. This is particularly true of importance sampli…
Etalumis: Bringing Probabilistic Programming to Scientific Simulators at Scale
Atılım Güneş Baydin, Lei Shao, Wahid Bhimji +14
Probabilistic programming languages (PPLs) are receiving widespread attention for performing Bayesian inference in complex generative models. However, applications to science remai…
The Thermodynamic Variational Objective
Vaden Masrani, Tuan Anh Le, Frank Wood
We introduce the thermodynamic variational objective (TVO) for learning in both continuous and discrete deep generative models. The TVO arises from a key connection between variati…
LF-PPL: A Low-Level First Order Probabilistic Programming Language for Non-Differentiable Models
Yuan Zhou, Bradley J. Gram-Hansen, Tobias Kohn +3
We develop a new Low-level, First-order Probabilistic Programming Language (LF-PPL) suited for models containing a mix of continuous, discrete, and/or piecewise-continuous variable…
Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model
Atılım Güneş Baydin, Lukas Heinrich, Wahid Bhimji +12
We present a novel probabilistic programming framework that couples directly to existing large-scale simulators through a cross-platform probabilistic execution protocol, which all…
Using Synthetic Data to Train Neural Networks is Model-Based Reasoning
Tuan Anh Le, Atilim Gunes Baydin, Robert Zinkov +1
We draw a formal connection between using synthetic training data to optimize neural network parameters and approximate, Bayesian, model-based reasoning. In particular, training a…
Online Learning Rate Adaptation with Hypergradient Descent
Atilim Gunes Baydin, Robert Cornish, David Martinez Rubio +2
We introduce a general method for improving the convergence rate of gradient-based optimizers that is easy to implement and works well in practice. We demonstrate the effectiveness…