Learning Stochastic Inverses

By Andreas Stuhlmüller, Jessica Taylor, Noah D. Goodman. 2013

120 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Generative Models

Citations in the corpus

What can the brain teach us about building artificial intelligence? (2016, neutral): “Mnih & Gregor, 2014; Rezende, Mohamed, & Wierstra, 2014) or nearest-neighbor density estimation (Kulkarni, Kohli, et al., 2015; Stuhlmüller et al., 2013).”
Variational Inference with Normalizing Flows (2015, methodology): “A second important practice is that the approximate posterior distribution qφ(·) is represented using a recognition model or inference network (Stuhlmüller et al., 2013; Rezende et al., 2014; Dayan, 2000; Gershman & Goodman, 2014; Kingma & Welling, 2014).”
Deep Unsupervised Learning using Nonequilibrium Thermodynamics (2015, background): “In (Stuhlmüller et al., 2013) stochastic inverses are learned for Bayesian networks.”
Foundation Posteriors for Approximate Probabilistic Inference (2022, positive): “Amortized inference [26, 55] was proposed as a more efﬁcient alternative by learning a function q ( z x ) that maps a observed assignment x to a distribution over the latent variable z .”
An Introduction to Probabilistic Programming (2018, background): “Chief amongst them is: is there a way to structure the bottomup program advantageously and automatically given the top-down program or vice versa? Important initial work has been done on this problem (Webb et al., 2017; Paige and Wood, 2016; Stuhlmüller et al., 2013) but much remains.”
DeepCoder: Learning to Write Programs (2016, background): “4.5 provides theoretical indication that ignoring the correlations between functions is not cataclysmic for Sort and add enumeration, since a Rank loss that upper bounds the Sort and add runtime can still be minimized.”
Learning Disentangled Representations with Semi-Supervised Deep Generative Models (2017, background): “This approach allows us also amortise inference [7, 23, 29, 34], simultaneously learning a network that performs approximate inference over representations at the same time we learn the unknown factors of the model itself.”
Variational Inference of Disentangled Latent Concepts from Unlabeled Observations (2017, background): “…inference of disentangled latent factors based on the popular and scalable framework of amortized variational inference (Kingma and Welling, 2013; Stuhlm¨uller et al., 2013; Gershman and Goodman, 2014; Rezende et al., 2014) powered by stochastic optimization (Hoﬀman et al., 2013; Kingma and…”
Hierarchical Variational Models (2015, background): “Inference networks (Dayan, 2000; Stuhlmüller et al., 2013; Kingma and Welling, 2014; Rezende et al., 2014) amortize the cost of estimating these local variational parameters by tying them together through a neural network.”
Automatic differentiation in machine learning: a survey (2015, methodology): “Amortized inference (Gershman and Goodman, 2014; Stuhlmüller et al., 2013) techniques based on deep learning (Le et al.”
Picture: A probabilistic programming language for scene perception (2015, background): “Such techniques fall under the broader idea of amortizing or caching inference to improve speed and accuracy [40].”
Edward: A library for probabilistic modeling, inference, and criticism (2016, background): “, 1995), also known as amortized inference (Stuhlmüller et al., 2013).”
Deep Amortized Inference for Probabilistic Programs (2016, background): “And for models in which there is a natural hierarchy between the latent variables and the observed variables, having the guide run ‘backwards’ from the observed variables to the top-most latents has been shown to be useful [28, 22, 20].”
Meta-Learning an Inference Algorithm for Probabilistic Programs (2021, background): “Amortised inference and inference compilation (Gershman & Goodman, 2014; Le et al., 2017; Paige & Wood, 2016; Stuhlmüller et al., 2013; Kingma & Welling, 2013; Mnih & Gregor, 2014; Rezende et al., 2014; Ritchie et al., 2016; Marino et al., 2018) are closely related to our approach in that they also ”
The informed sampler: A discriminative approach to Bayesian inference in generative computer vision models (2014, methodology): “Another piece of work from [41] is similar to our proposed inference method in that knowledge about the forward process is learned as ‘‘stochastic inverses’’, then applied for MCMC sampling in a Bayesian network.”
How to marry a star: Probabilistic constraints for meaning in context (2020, methodology): “More realistic systems will require techniques like amortized inference, basically inverting the graphical model (Stuhlmüller et al. 2013).”
Gen: a general-purpose probabilistic programming system with programmable inference (2019, methodology): “…using generic or custom proposal distributions, MAP optimization using gradients, training proposal distributions using amortized inference [59], particle filtering [15] including custom proposals and rejuve-nation moves, MALA [52], Hamiltonian Monte Carlo [16], custom reversible jump MCMC…”
Amortized Inference in Probabilistic Reasoning (2014, methodology): “Stuhlmüller et al. (2013) proposed a more sophisticated framework for reusing samples within MCMC.”