Fetching the paper…
Reading the bibliography…
Several first order stochastic optimization methods commonly used in the Euclidean domain such as stochastic gradient descent (SGD), accelerated gradient descent or variance reduced methods have already been adapted to certain Riemannian settings.
Morse Theory.(AM-51) , volume 51
John Milnor · 1963
Earlier work this paper cites.
A comprehensive introduction to differential geometry. volume four
Michael Spivak · 1979
Earlier work this paper cites.
Hyperbolic groups
Mikhael Gromov · 1987
Earlier work this paper cites.
Introduction to wordnet: An on-line lexical database
George A Miller, Richard Beckwith, Christiane Fellbaum, Derek Gross, and Katherine J Miller · 1990
Earlier work this paper cites.
Adaptive and self-confident on-line learning algorithms
Peter Auer, Nicolo Cesa-Bianchi, and Claudio Gentile · 2002
Earlier work this paper cites.
A gyrovector space approach to hyperbolic geometry
Abraham Albert Ungar · 2008
Earlier work this paper cites.
A riemannian optimization approach for computing low-rank solutions of lyapunov equations
Bart Vandereycken and Stefan Vandewalle · 2010
Earlier work this paper cites.
Adaptive subgradient methods for online learning and stochastic optimization
John Duchi, Elad Hazan, and Yoram Singer · 2011
Earlier work this paper cites.
Introduction to differential geometry
Joel W Robbin and Dietmar A Salamon · 2011
Earlier work this paper cites.
Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude
Tijmen Tieleman and Geoffrey Hinton · 2012
Earlier work this paper cites.
Adadelta: an adaptive learning rate method
Matthew D Zeiler · 2012
Earlier work this paper cites.
Stochastic gradient descent on riemannian manifolds
Silvere Bonnabel · 2013
Cited alongside, same era.
Stochastic gradient riemannian langevin dynamics on the probability simplex
Sam Patterson and Yee Whye Teh · 2013
Cited alongside, same era.
Glove: Global vectors for word representation
Jeffrey Pennington, Richard Socher, and Christopher D Manning · 2014
Cited alongside, same era.
Riemannian pursuit for big matrix recovery
Mingkui Tan, Ivor W Tsang, Li Wang, Bart Vandereycken, and Sinno Jialin Pan · 2014
Cited alongside, same era.
Adam: A method for stochastic optimization
Diederik P Kingma and Jimmy Ba · 2015
Cited alongside, same era.
Conic geometric optimization on the manifold of positive definite matrices
Suvrit Sra and Reshad Hosseini · 2015
Cited alongside, same era.
Riemannian stein variational gradient descent for bayesian inference
Chang Liu and Jun Zhu · 2017
Later among the works it cites.
Accelerated first-order methods for geodesically convex optimization on riemannian manifolds
Yuanyuan Liu, Fanhua Shang, James Cheng, Hong Cheng, and Licheng Jiao · 2017
Later among the works it cites.
Poincaré embeddings for learning hierarchical representations
Maximillian Nickel and Douwe Kiela · 2017
Later among the works it cites.
Representation tradeoffs for hyperbolic embeddings
Christopher De Sa, Albert Gu, Christopher Ré, and Frederic Sala · 2018
Closest in time.
Learning continuous hierarchies in the lorentz model of hyperbolic geometry
Maximilian Nickel and Douwe Kiela · 2018
Closest in time.
On the convergence of adam and beyond
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
First-order methods for geodesically convex optimization
Hongyi Zhang and Suvrit Sra · 2016
Cited alongside, same era.
Riemannian svrg: Fast stochastic optimization on riemannian manifolds
Hongyi Zhang, Sashank J Reddi, and Suvrit Sra · 2016
Cited alongside, same era.
Riemannian dictionary learning and sparse coding for positive definite matrices
Anoop Cherian and Suvrit Sra · 2017
Cited alongside, same era.
Riemannian approach to batch normalization
Minhyung Cho and Jaehyung Lee · 2017
Cited alongside, same era.
Hyperbolic entailment cones for learning hierarchical embeddings
Octavian-Eugen Ganea, Gary Bécigneul, and Thomas Hofmann
Cited in the paper.
Hyperbolic neural networks
Octavian-Eugen Ganea, Gary Bécigneul, and Thomas Hofmann
Cited in the paper.
Sashank J Reddi, Satyen Kale, and Sanjiv Kumar · 2018
Closest in time.
Geometry aware constrained optimization techniques for deep learning
S Kumar Roy, Zakaria Mhammedi, and Mehrtash Harandi · 2018
Closest in time.
Averaging stochastic gradient descent on riemannian manifolds
Nilesh Tripuraneni, Nicolas Flammarion, Francis Bach, and Michael I Jordan · 2018
Closest in time.
Hyperbolic recommender systems
Tran Dang Quang Vinh, Yi Tay, Shuai Zhang, Gao Cong, and Xiao-Li Li · 2018
Closest in time.
Towards riemannian accelerated gradient methods
Hongyi Zhang and Suvrit Sra · 2018
Closest in time.