Fetching the paper…
Reading the bibliography…
Stochastic Gradient Langevin Dynamics (SGLD) is a powerful algorithm for optimizing a non-convex objective, where a controlled and properly scaled Gaussian noise is added to the stochastic gradients to steer the iterates towards a global minimum.
A Harnack inequality for parabolic differential equations
Jürgen Moser · 1964
Earlier work this paper cites.
Local behavior of solutions of quasilinear parabolic equations
Donald G. Aronson and James Serrin · 1967
Earlier work this paper cites.
Pointwise estimates and quasilinear parabolic equations
Neil S. Trudinger · 1968
Earlier work this paper cites.
Mimicking the one-dimensional marginal distributions of processes having an Itô differential
István Gyöngy · 1986
Earlier work this paper cites.
Accelerating Gaussian diffusions
Chii-Ruey Hwang, Shu-Yin Hwang-Ma, and Shuenn-Jyi Sheu · 1993
Earlier work this paper cites.
Maximum likelihood and covariant algorithms for independent component analysis
David JC MacKay · 1996
Earlier work this paper cites.
Independent component analysis: algorithms and applications
A. Hyvärinen and E. Oja · 2000
Earlier work this paper cites.
Face recognition by independent component analysis
Marian Stewart Bartlett, Javier R. Movellan, and Terrence J. Sejnowski · 2002
Earlier work this paper cites.
An efficient iris recognition system
Ya-Ping Huang, Si-Wei Luo, and En-Yi Chen · 2002
Earlier work this paper cites.
Metastability in reversible diffusion processes II: Precise asymptotics for small eigenvalues
Anton Bovier, Véronique Gayrard, and Markus Klein · 2005
Earlier work this paper cites.
Weighted Csiszár-Kullback-Pinsker inequalities and applications to transportation inequalities
François Bolley and Cédric Villani · 2005
Earlier work this paper cites.
Accelerating diffusions
Chii-Ruey Hwang, Shu-Yin Hwang-Ma, and Shuenn-Jyi Sheu · 2005
Earlier work this paper cites.
Iris recognition using independent component analysis
Yong Wang and Jiu-Qiang Han · 2005
Cited alongside, same era.
Estimates of densities of stationary distributions and transition probabilities of diffusion processes
V. I. Bogachev, M. Röckner, and S. V. Shaposhnikov · 2008
Cited alongside, same era.
Independent component and pathway-based analysis of mirna-regulated gene expression in a model of type 1 diabetes
Claus H Bang-Berthelsen, Lykke Pedersen, Tina Fløyel, Peter H Hagedorn, Titus Gylvin, and Flemming Pociot · 2011
Cited alongside, same era.
Bayesian learning via stochastic gradient Langevin dynamics
Max Welling and Yee W Teh · 2011
Cited alongside, same era.
Analysis and geometry of Markov diffusion operators
Dominique Bakry, Ivan Gentil, and Michel Ledoux · 2013
Cited alongside, same era.
Variance reduction using nonreversible Langevin samplers
Andrew B. Duncan, T. Lelièvre, and Grigorios A. Pavliotis · 2016
Later among the works it cites.
Optimal linear drift for the speed of convergence of an hypoelliptic diffusion
Arnaud Guillin and Pierre Monmarché · 2016
Later among the works it cites.
Preconditioned stochastic gradient Langevin dynamics for deep neural networks
Chunyuan Li, Changyou Chen, David Carlson, and Lawrence Carin · 2016
Later among the works it cites.
Wasserstein continuity of entropy and outer bounds for interference channels
Yury Polyanskiy and Yihong Wu · 2016
Later among the works it cites.
Improving the convergence of reversible samplers
Luc Rey-Bellet and Konstantinos Spiliopoulos · 2016
Later among the works it cites.
Nonreversible Langevin samplers: Splitting schemes, analysis and implementation
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Sonja Cox, Martin Hutzenthaler, and Arnulf Jentzen · 2013
Cited alongside, same era.
Optimal non-reversible linear drift for the convergence to equilibrium of a diffusion
Tony Lelièvre, Francis Niew, and Grigorios A. Pavliotis · 2013
Cited alongside, same era.
The Nature of Statistical Learning Theory
Vladimir Vapnik · 2013
Cited alongside, same era.
Irreversible Langevin samplers and variance reduction: a large deviation approach
Luc Rey-Bellet and Konstantinos Spiliopoulos · 2014
Cited alongside, same era.
Attaining the optimal Gaussian diffusion acceleration
Sheng-Jhih Wu, Chii-Ruey Hwang, and Moody T. Chu · 2014
Cited alongside, same era.
A complete recipe for stochastic gradient MCMC
Yi-An Ma, Tianqi Chen, and Emily Fox · 2015
Cited alongside, same era.
Variance reduction for irreversible langevin samplers and diffusion on graphs
Luc Rey-Bellet and Konstantinos Spiliopoulos · 2015
Cited alongside, same era.
Andrew B. Duncan, Grigorios A. Pavliotis, and Konstantinos C. Zygalakis · 2017
Later among the works it cites.
Non-convex learning via stochastic gradient Langevin dynamics: A nonasymptotic analysis
Maxim Raginsky, Alexander Rakhlin, and Matus Telgarsky · 2017
Later among the works it cites.
Breaking reversibility accelerates Langevin dynamics for global non-convex optimization
Xuefeng Gao, Mert Gürbüzbalaban, and Lingjiong Zhu · 2018
Later among the works it cites.
Xuefeng Gao, Mert Gürbüzbalaban, and Lingjiong Zhu · 2018
Later among the works it cites.
The landscape of empirical risk for nonconvex losses
Song Mei, Yu Bai, and Andrea Montanari · 2018
Later among the works it cites.
Global convergence of Langevin dynamics based algorithms for nonconvex optimization
Pan Xu, Jinghui Chen, Difan Zou, and Quanquan Gu · 2018
Later among the works it cites.
Sharp spectral asymptotics for non-reversible metastable diffusion process
Dorian Le Peutrec and Laurent Michel · 2019
Later among the works it cites.