Stochastic Adaptive Quasi-Newton Methods for Minimizing Expected Values
By Chao Zhou, Wenbo Gao, Donald Goldfarb. 2017
26 citations recorded by the source corpus.
Subfields: Optimization & Training
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Optimization & Training
- Peter Richtárik
- Simon Lacoste-Julien
- Nicolas Loizou
- Issam Hadj Laradji
- Mark W. Schmidt
- Francis R. Bach
- Sharan Vaswani
- Robert Mansel Gower
Citations in the corpus
- Fast and Furious Convergence: Stochastic Second Order Methods under Interpolation (2019, methodology): “Next, we study stochastic Quasi-Newton meth-ods (Schraudolph et al., 2007; Sunehag et al., 2009; Zhou et al., 2017; Liu et al., 2018; Berahas et al., 2019; Gao and Goldfarb, 2019) in the interpolation setting (Section 5).”
- A Progressive Batching L-BFGS Method for Machine Learning (2018, methodology): “Stochastic second-order methods have been explored within the context of convex and non-convex optimization; see (Schraudolph et al., 2007; Sohl-Dickstein et al., 2014; Mokhtari & Ribeiro, 2015; Berahas et al., 2016; Byrd et al., 2016; Keskar & Berahas, 2016; Curtis, 2016; Berahas & Takáč, 2017; Zho”
- Quasi-Newton methods: superlinear convergence without line searches for self-concordant functions (2016, methodology): “Note: the stochastic adaptive BFGS analyzed in [27] is slightly different, as it incorporates an additional Wolfe condition test.”
- Finite-sample Analysis of M-estimators using Self-concordance (2018, methodology): “ce" scheme proposed in [Meh17]. Finally, we should mention the recent surge of interest in stochastic quasi-Newton methods applied to the nite-sum setting with self-concordant losses, see, e.g., [ZGG17], [ZL15]. However, none of these works is concerned with establishing the asymptotically opti”
- Asynchronous Stochastic Quasi-Newton MCMC for Non-Convex Optimization (2018, methodology): “As a remedy, stochastic L-BGFS methods have been proposed (Byrd et al., 2016; Schraudolph et al., 2007; Moritz et al., 2016; Zhou et al., 2017; Yousefian et al., 2017; Zhao et al., 2017), which aim to reduce the computational requirements of L-BFGS by replacing ∇U (i.”