Fetching the paper…
Reading the bibliography…
We propose a new algorithm for minimizing regularized empirical loss: Stochastic Dual Newton Ascent (SDNA).
A stochastic quasi-newton method for online convex optimization
Schraudolph, Nicol N., Yu, Jin, and Günter, Simon · 2007
Earlier work this paper cites.
Sgd-qn: Careful quasi-newton stochastic gradient descent
Bordes, Antoine, Bottou, Léon, and Gallinari, Patrick · 2009
Earlier work this paper cites.
Pegasos: Primal estimated sub-gradient solver for SVM
Shalev-Shwartz, Shai, Singer, Yoram, Srebro, Nati, and Cotter, Andrew · 2011
Earlier work this paper cites.
Parallel coordinate descent methods for big data optimization problems
Richtárik, Peter and Takáč, Martin · 2012
Earlier work this paper cites.
Accelerating stochastic gradient descent using predictive variance reduction
Johnson, Rie and Zhang, Tong · 2013
Earlier work this paper cites.
Minimizing finite sums with the stochastic average gradient
Schmidt, Mark, Le Roux, Nicolas, and Bach, Francis · 2013
Earlier work this paper cites.
Mini-batch primal and dual methods for SVMs
Takáč, Martin, Bijral, Avleen, Richtárik, Peter, and Srebro, Nathan · 2013
Earlier work this paper cites.
Inexact block coordinate descent method: complexity and preconditioning
Tappenden, Rachael, Richtárik, Peter, and Gondzio, Jacek · 2013
Earlier work this paper cites.
A stochastic quasi-newton method for large-scale optimization
Byrd, R.H., Hansen, S.L., Nocedal, Jorge, and Singer, Yoram · 2014
Cited alongside, same era.
Saga: A fast incremental gradient method with support for non-strongly convex composite objectives
Defazio, Aaron, Bach, Francis, and Lacoste-Julien, Simon · 2014
Cited alongside, same era.
Fast distributed coordinate descent for minimizing non-strongly convex losses
Fercoq, Olivier, Qu, Zheng, Richtárik, Peter, and Takáč, Martin · 2014
Cited alongside, same era.
Robust block coordinate descent
Fountoulakis, Kimon and Tappenden, Rachael · 2014
Cited alongside, same era.
Randomized dual coordinate ascent with arbitrary sampling
Qu, Zheng, Richtárik, Peter, and Zhang, Tong · 2014
Later among the works it cites.
Iteration complexity of randomized block-coordinate descent methods for minimizing a composite function
Richtárik, Peter and Takáč, Martin · 2014
Later among the works it cites.
Understanding Machine Learning: From Theory to Algorithms
Shalev-Shwartz, Shai and Ben-David, Shai · 2014
Later among the works it cites.
Fast large-scale optimization by unifying stochastic gradient and quasi-newton methods
Sohl-Dickstein, Jascha, Poole, Ben, and Ganguli, Surya · 2014
Later among the works it cites.
Separable approximations and decomposition methods for the augmented lagrangian
Tappenden, Rachael, Richtárik, Peter, and Büke, Burak · 2014
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Konečný, Jakub and Richtárik, Peter · 2014
Cited alongside, same era.
An accelerated proximal coordinate gradient method and its application to regularized empirical risk minimization
Lin, Qihang, Lu, Zhaosong, and Xiao, Lin · 2014
Cited alongside, same era.
Incremental majorization-minimization optimization with application to large-scale machine learning
Mairal, Julien · 2014
Cited alongside, same era.
Iterative Hessian sketch: Fast and accurate solution approximation for constrained least-squares
Pilanci, Mert and Wainwright, Martin J · 2014
Cited alongside, same era.
Accelerated, parallel and proximal coordinate descent
Fercoq, Olivier and Richtárik, Peter
Cited in the paper.
Smooth minimization of nonsmooth functions by parallel coordinate descent
Fercoq, Olivier and Richtárik, Peter
Cited in the paper.
mS2GD: Mini-batch semi-stochastic gradient descent in the proximal setting
Konečný, Jakub, Lu, Jie, Richtárik, Peter, and Takáč, Martin
Cited in the paper.
Semi-stochastic coordinate descent
Konečný, Jakub, Qu, Zheng, and Richtárik, Peter
Cited in the paper.
Xiao, Lin and Zhang, Tong · 2014
Later among the works it cites.
Stochastic optimization with importance sampling
Zhao, Peilin and Zhang, Tong · 2014
Later among the works it cites.
Distributed coordinate descent method for learning with big data
Richtárik, Peter and Takáč, Martin · 2059
Closest in time.