Timezone: »
Many probabilistic modeling problems in machine learning use gradient-based optimization in which the objective takes the form of an expectation. These problems can be challenging when the parameters to be optimized determine the probability distribution under which the expectation is being taken, as the na\"ive Monte Carlo procedure is not differentiable. Reparameterization gradients make it possible to efficiently perform optimization of these Monte Carlo objectives by transforming the expectation to be differentiable, but the approach is typically limited to distributions with simple forms and tractable normalization constants. Here we describe how to differentiate samples from slice sampling to compute \textit{slice sampling reparameterization gradients}, enabling a richer class of Monte Carlo objective functions to be optimized. Slice sampling is a Markov chain Monte Carlo algorithm for simulating samples from probability distributions; it only requires a density function that can be evaluated point-wise up to a normalization constant, making it applicable to a variety of inference problems and unnormalized models. Our approach is based on the observation that when the slice endpoints are known, the sampling path is a deterministic and differentiable function of the pseudo-random variables, since the algorithm is rejection-free. We evaluate the method on synthetic examples and apply it to a variety of applications with reparameterization of unnormalized probability distributions.
Author Information
David Zoltowski (University of Cambridge)
Diana Cai (Princeton University)
Ryan Adams (Princeton University)
Related Events (a corresponding poster, oral, or spotlight)
-
2021 Poster: Slice Sampling Reparameterization Gradients »
Fri. Dec 10th 12:30 -- 02:00 AM Room
More from the Same Authors
-
2021 Spotlight: Amortized Synthesis of Constrained Configurations Using a Differentiable Surrogate »
Xingyuan Sun · Tianju Xue · Szymon Rusinkiewicz · Ryan Adams -
2021 : Neural Latents Benchmark ‘21: Evaluating latent variable models of neural population activity »
Felix Pei · Joel Ye · David Zoltowski · Anqi Wu · Raeed Chowdhury · Hansem Sohn · Joseph O'Doherty · Krishna V Shenoy · Matthew Kaufman · Mark Churchland · Mehrdad Jazayeri · Lee Miller · Jonathan Pillow · Il Memming Park · Eva Dyer · Chethan Pandarinath -
2021 : ProBF: Probabilistic Safety Certificates with Barrier Functions »
Sulin Liu · Athindran Ramesh Kumar · Jaime Fisac · Ryan Adams · Peter J. Ramadge -
2021 : Reading the Road: Leveraging Meta-Learning to Learn Other Driver Behavior »
Anat Kleiman · Ryan Adams -
2022 : Multi-fidelity Bayesian experimental design using power posteriors »
Andrew Jones · Diana Cai · Barbara Engelhardt -
2022 : Kernel Density Bayesian Inverse Reinforcement Learning »
Aishwarya Mandyam · Didong Li · Diana Cai · Andrew Jones · Barbara Engelhardt -
2022 : A code superoptimizer through neural Monte-Carlo tree search »
Wenda Zhou · Olga Solodova · Ryan Adams -
2022 : A code superoptimizer through neural Monte-Carlo tree search »
Wenda Zhou · Olga Solodova · Ryan Adams -
2022 Poster: Multi-fidelity Monte Carlo: a pseudo-marginal approach »
Diana Cai · Ryan Adams -
2021 : Randomized Automatic Differentiation - Ryan Adams - Princeton University »
Ryan Adams -
2021 Workshop: Your Model is Wrong: Robustness and misspecification in probabilistic modeling »
Diana Cai · Sameer Deshpande · Michael Hughes · Tamara Broderick · Trevor Campbell · Nick Foti · Barbara Engelhardt · Sinead Williamson -
2021 Poster: Amortized Synthesis of Constrained Configurations Using a Differentiable Surrogate »
Xingyuan Sun · Tianju Xue · Szymon Rusinkiewicz · Ryan Adams -
2021 Poster: Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability »
Dibya Ghosh · Jad Rahme · Aviral Kumar · Amy Zhang · Ryan Adams · Sergey Levine -
2020 : Orals 1.1: Randomized Automatic Differentiation »
Deniz Oktay · Nick McGreivy · Alex Beatson · Ryan Adams -
2020 Workshop: Machine Learning for Engineering Modeling, Simulation and Design »
Alex Beatson · Priya Donti · Amira Abdel-Rahman · Stephan Hoyer · Rose Yu · J. Zico Kolter · Ryan Adams -
2020 Poster: On Warm-Starting Neural Network Training »
Jordan Ash · Ryan Adams -
2020 Poster: Task-Agnostic Amortized Inference of Gaussian Process Hyperparameters »
Sulin Liu · Xingyuan Sun · Peter J. Ramadge · Ryan Adams -
2020 Poster: Learning Composable Energy Surrogates for PDE Order Reduction »
Alex Beatson · Jordan Ash · Geoffrey Roeder · Tianju Xue · Ryan Adams -
2020 Oral: Learning Composable Energy Surrogates for PDE Order Reduction »
Alex Beatson · Jordan Ash · Geoffrey Roeder · Tianju Xue · Ryan Adams -
2019 : Break / Poster Session 1 »
Antonia Marcu · Yao-Yuan Yang · Pascale Gourdeau · Chen Zhu · Thodoris Lykouris · Jianfeng Chi · Mark Kozdoba · Arjun Nitin Bhagoji · Xiaoxia Wu · Jay Nandy · Michael T Smith · Bingyang Wen · Yuege Xie · Konstantinos Pitas · Suprosanna Shit · Maksym Andriushchenko · Dingli Yu · Gaël Letarte · Misha Khodak · Hussein Mozannar · Chara Podimata · James Foulds · Yizhen Wang · Huishuai Zhang · Ondrej Kuzelka · Alexander Levine · Nan Lu · Zakaria Mhammedi · Paul Viallard · Diana Cai · Lovedeep Gondara · James Lucas · Yasaman Mahdaviyeh · Aristide Baratin · Rishi Bommasani · Alessandro Barp · Andrew Ilyas · Kaiwen Wu · Jens Behrmann · Omar Rivasplata · Amir Nazemi · Aditi Raghunathan · Will Stephenson · Sahil Singla · Akhil Gupta · YooJung Choi · Yannic Kilcher · Clare Lyle · Edoardo Manino · Andrew Bennett · Zhi Xu · Niladri Chatterji · Emre Barut · Flavien Prost · Rodrigo Toro Icarte · Arno Blaas · Chulhee Yun · Sahin Lale · YiDing Jiang · Tharun Kumar Reddy Medini · Ashkan Rezaei · Alexander Meinke · Stephen Mell · Gary Kazantsev · Shivam Garg · Aradhana Sinha · Vishnu Lokhande · Geovani Rizk · Han Zhao · Aditya Kumar Akash · Jikai Hou · Ali Ghodsi · Matthias Hein · Tyler Sypherd · Yichen Yang · Anastasia Pentina · Pierre Gillot · Antoine Ledent · Guy Gur-Ari · Noah MacAulay · Tianzong Zhang -
2019 Poster: SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers »
Igor Fedorov · Ryan Adams · Matthew Mattina · Paul Whatmough -
2019 Poster: Discrete Object Generation with Reversible Inductive Construction »
Ari Seff · Wenda Zhou · Farhan Damani · Abigail Doyle · Ryan Adams -
2018 : Discussion Panel: Ryan Adams, Nicolas Heess, Leslie Kaelbling, Shie Mannor, Emo Todorov (moderator: Roy Fox) »
Ryan Adams · Nicolas Heess · Leslie Kaelbling · Shie Mannor · Emo Todorov · Roy Fox -
2018 : Inference and Control of Learning Behavior in Rodents (Ryan Adams) »
Ryan Adams -
2018 Poster: A Bayesian Nonparametric View on Count-Min Sketch »
Diana Cai · Michael Mitzenmacher · Ryan Adams -
2017 Poster: PASS-GLM: polynomial approximate sufficient statistics for scalable Bayesian GLM inference »
Jonathan Huggins · Ryan Adams · Tamara Broderick -
2017 Spotlight: PASS-GLM: polynomial approximate sufficient statistics for scalable Bayesian GLM inference »
Jonathan Huggins · Ryan Adams · Tamara Broderick -
2017 Poster: Reducing Reparameterization Gradient Variance »
Andrew Miller · Nick Foti · Alexander D'Amour · Ryan Adams -
2016 : Panel Discussion »
Shakir Mohamed · David Blei · Ryan Adams · José Miguel Hernández-Lobato · Ian Goodfellow · Yarin Gal -
2016 : A Tribute to David MacKay »
Ryan Adams -
2016 Workshop: Bayesian Optimization: Black-box Optimization and Beyond »
Roberto Calandra · Bobak Shahriari · Javier Gonzalez · Frank Hutter · Ryan Adams -
2016 : Leveraging Structure in Bayesian Optimization »
Ryan Adams -
2016 Poster: Bayesian latent structure discovery from multi-neuron recordings »
Scott Linderman · Ryan Adams · Jonathan Pillow -
2016 Poster: Composing graphical models with neural networks for structured representations and fast inference »
Matthew Johnson · David Duvenaud · Alex Wiltschko · Ryan Adams · Sandeep R Datta -
2015 Workshop: Bayesian Optimization: Scalability and Flexibility »
Bobak Shahriari · Ryan Adams · Nando de Freitas · Amar Shah · Roberto Calandra -
2015 Workshop: Statistical Methods for Understanding Neural Systems »
Alyson Fletcher · Jakob H Macke · Ryan Adams · Jascha Sohl-Dickstein -
2015 Poster: Convolutional Networks on Graphs for Learning Molecular Fingerprints »
David Duvenaud · Dougal Maclaurin · Jorge Iparraguirre · Rafael Bombarell · Timothy Hirzel · Alan Aspuru-Guzik · Ryan Adams -
2015 Poster: A Gaussian Process Model of Quasar Spectral Energy Distributions »
Andrew Miller · Albert Wu · Jeffrey Regier · Jon McAuliffe · Dustin Lang · Mr. Prabhat · David Schlegel · Ryan Adams -
2015 Poster: Spectral Representations for Convolutional Neural Networks »
Oren Rippel · Jasper Snoek · Ryan Adams -
2015 Poster: Dependent Multinomial Models Made Easy: Stick-Breaking with the Polya-gamma Augmentation »
Scott Linderman · Matthew Johnson · Ryan Adams -
2014 Workshop: Bayesian Optimization in Academia and Industry »
Zoubin Ghahramani · Ryan Adams · Matthew Hoffman · Kevin Swersky · Jasper Snoek -
2014 Poster: A framework for studying synaptic plasticity with neural spike train data »
Scott Linderman · Christopher H Stock · Ryan Adams -
2013 Workshop: Bayesian Optimization in Theory and Practice »
Matthew Hoffman · Jasper Snoek · Nando de Freitas · Michael A Osborne · Ryan Adams · Sebastien Bubeck · Philipp Hennig · Remi Munos · Andreas Krause -
2013 Poster: Multi-Task Bayesian Optimization »
Kevin Swersky · Jasper Snoek · Ryan Adams -
2013 Poster: Message Passing Inference with Chemical Reaction Networks »
Nils E Napp · Ryan Adams -
2013 Oral: Message Passing Inference with Chemical Reaction Networks »
Nils E Napp · Ryan Adams -
2013 Poster: A Determinantal Point Process Latent Variable Model for Inhibition in Neural Spiking Data »
Jasper Snoek · Richard Zemel · Ryan Adams -
2013 Poster: Contrastive Learning Using Spectral Methods »
James Y Zou · Daniel Hsu · David Parkes · Ryan Adams -
2012 Poster: Bayesian n-Choose-k Models for Classification and Ranking »
Kevin Swersky · Danny Tarlow · Richard Zemel · Ryan Adams · Brendan J Frey -
2012 Poster: Priors for Diversity in Generative Latent Variable Models »
James Y Zou · Ryan Adams -
2012 Poster: Cardinality Restricted Boltzmann Machines »
Kevin Swersky · Danny Tarlow · Ilya Sutskever · Richard Zemel · Russ Salakhutdinov · Ryan Adams -
2012 Poster: Practical Bayesian Optimization of Machine Learning Algorithms »
Jasper Snoek · Hugo Larochelle · Ryan Adams -
2011 Workshop: Bayesian Nonparametric Methods: Hope or Hype? »
Emily Fox · Ryan Adams -
2010 Workshop: Transfer Learning Via Rich Generative Models. »
Russ Salakhutdinov · Ryan Adams · Josh Tenenbaum · Zoubin Ghahramani · Tom Griffiths -
2010 Workshop: Monte Carlo Methods for Bayesian Inference in Modern Day Applications »
Ryan Adams · Mark A Girolami · Iain Murray -
2010 Oral: Tree-Structured Stick Breaking for Hierarchical Data »
Ryan Adams · Zoubin Ghahramani · Michael Jordan -
2010 Oral: Slice sampling covariance hyperparameters of latent Gaussian models »
Iain Murray · Ryan Adams -
2010 Poster: Tree-Structured Stick Breaking for Hierarchical Data »
Ryan Adams · Zoubin Ghahramani · Michael Jordan -
2010 Poster: Slice sampling covariance hyperparameters of latent Gaussian models »
Iain Murray · Ryan Adams -
2008 Poster: The Gaussian Process Density Sampler »
Ryan Adams · Iain Murray · David MacKay -
2008 Spotlight: The Gaussian Process Density Sampler »
Ryan Adams · Iain Murray · David MacKay