Early Stopping is Nonparametric Variational Inference

Dougal Maclaurin, David Duvenaud, Ryan P. Adams

Type: Preprint

Publication Date: 2015-01-01

Citations: 12

DOI: https://doi.org/10.48550/arxiv.1504.01344

View Publication

Locations

arXiv (Cornell University) - View
DataCite API - View

Similar Works

Action	Title	Year	Authors
+	Early Stopping as Nonparametric Variational Inference	2016	David Duvenaud Dougal Maclaurin Ryan P. Adams
+	Gradient Regularisation as Approximate Variational Inference	2020	Ali Ünlü Laurence Aitchison
+	Differentiable Annealed Importance Sampling and the Perils of Gradient Noise	2021	Guodong Zhang Kyle Hsu Jianing Li Chelsea Finn Roger Grosse
+	A variational analysis of stochastic gradient algorithms	2016	Stephan Mandt Matthew D. Hoffman David M. Blei
+	A Variational Analysis of Stochastic Gradient Algorithms	2016	Stephan Mandt Matthew D. Hoffman David M. Blei
+	Importance Sampled Stochastic Optimization for Variational Inference	2017	Joseph Sakaya Arto Klami
+	Kalman Gradient Descent: Adaptive Variance Reduction in Stochastic Optimization	2018	James Vuckovic
+	Convergence Rates of Variational Inference in Sparse Deep Learning	2019	Badr-Eddine Chérief-Abdellatif
+	Why do Gradient Methods Work in Optimization and Sampling	2021	Niladri S. Chatterji
+ PDF Chat	Batch and match: black-box variational inference with a score-based divergence	2024	Diana Cai Chirag Modi Loucas Pillaud-Vivien Charles C. Margossian Robert M. Gower David M. Blei Lawrence K. Saul
+	Improved Gradient-Based Optimization Over Discrete Distributions	2018	Evgeny Andriyash Arash Vahdat William G. Macready
+	Improving Explorability in Variational Inference with Annealed Variational Objectives	2018	Chin-Wei Huang Shawn Tan Alexandre Lacoste Aaron Courville
+	Improving Explorability in Variational Inference with Annealed Variational Objectives	2018	Chin-Wei Huang Shawn Tan Alexandre Lacoste Aaron Courville
+	Fast Second-Order Stochastic Backpropagation for Variational Inference	2015	Kai Fan Ziteng Wang Jeffrey Beck James T. Kwok Katherine Heller
+	Sticking the Landing: Simple, Lower-Variance Gradient Estimators for Variational Inference	2017	Geoffrey Roeder Yuhuai Wu David Duvenaud
+	Sticking the Landing: Simple, Lower-Variance Gradient Estimators for Variational Inference	2017	Geoffrey Roeder Yuhuai Wu David Duvenaud
+ PDF Chat	Sequential Monte Carlo for Inclusive KL Minimization in Amortized Variational Inference	2024	Declan McNamara Jackson Loper Jeffrey Regier
+ PDF Chat	Scalable estimation strategies based on stochastic approximations: classical results and new insights	2015	Panos Toulis Edoardo M. Airoldi
+ PDF Chat	Robust, Accurate Stochastic Optimization for Variational Inference	2020	Akash Kumar Dhaka Alejandro Catalina Michael Riis Andersen Måns Magnusson Jonathan H. Huggins Aki Vehtari
+	Robust, Accurate Stochastic Optimization for Variational Inference	2020	Akash Kumar Dhaka Alejandro Catalina Michael Riis Andersen Måns Magnusson Jonathan H. Huggins Aki Vehtari

Works That Cite This (6)

Action	Title	Year	Authors
+	A Variational Analysis of Stochastic Gradient Algorithms	2016	Stephan Mandt Matthew D. Hoffman David M. Blei
+	Learning to Draw Samples with Amortized Stein Variational Gradient Descent	2017	Yihao Feng Dilin Wang Qiang Liu
+	Channel Distillation: Channel-Wise Attention for Knowledge Distillation	2020	Zaida Zhou Chaoran Zhuge Xinwei Guan Wen Liu
+	Known Unknowns: Uncertainty Quality in Bayesian Neural Networks	2016	Ramón de Oliveira Pedro Tabacof Eduardo Valle
+	Errors-in-Variables for deep learning: rethinking aleatoric uncertainty.	2021	Jörg Martin Clemens Elster
+	Early Stopping without a Validation Set.	2017	Maren Mahsereci Lukas Balles Christoph Lassner Philipp Hennig

Works Cited by This (7)

Action	Title	Year	Authors
+	Early stopping and non-parametric regression: an optimal data-dependent stopping rule	2014	Garvesh Raskutti Martin J. Wainwright Bin Yu
+ PDF Chat	Estimation of the Mean of a Multivariate Normal Distribution	1981	Charles Stein
+	Estimating the partition function of graphical models using Langevin importance sampling	2013	Jianzhu Ma Jian Peng Sheng Wang Jinbo Xu
+	Bayesian Learning via Stochastic Gradient Langevin Dynamics	2011	Max Welling Yee Whye Teh
+	Markov Chain Monte Carlo and Variational Inference: Bridging the Gap	2014	Tim Salimans Diederik P. Kingma Max Welling
+	Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks	2015	José Miguel Hernández-Lobato Ryan P. Adams
+	Nested Variational Compression in Deep Gaussian Processes	2014	James Hensman Neil D. Lawrence