Complexity and global rates of trust-region methods based on probabilistic models

By Serge Gratton, Clément W. Royer, Luís Nunes Vicente, Zaikun Zhang. 2018

79 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Management Science and Operations Research, 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 Artificial Intelligence

In Management Science and Operations Research

In Optimization & Training

Citations in the corpus

Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates (2019, background): “Other work [11, 26] exploring trust-region methods assume that the model is sufficiently accurate, which is not guaranteed in the general stochastic setting.”
Adaptive norms for deep learning with regularized Newton methods (2019, methodology): “Recently, stochastic extensions have emerged (Xu et al., 2017b; Yao et al., 2018; Kohler & Lucchi, 2017; Gratton et al., 2017), which suggest their applicability for deep learning.”
Optimization Methods for Supervised Machine Learning: From Linear Models to Deep Learning (2017, background): “Recently, in a series of papers [3, 15, 34], trust region, line search, and adaptive cubic regularization methods have been analyzed in convex and nonconvex cases using a very general framework of random models.”
A Subsampling Line-Search Method with Second-Order Results (2018, methodology): “When exact function values can be computed, one can employ strategies based on line search [15], cubic regularization [15, 27] or trust region [18, 24] to compute a step of suitable length.”
Convergence Rate Analysis of a Stochastic Trust-Region Method via Supermartingales (2019, methodology): “This paper can be seen as an extension of Cartis and Scheinberg (2018) and Gratton et al. (2017) to a fully stochastic setting.”
Ellipsoidal Trust Region Methods and the Marginal Value of Hessian Information for Neural Network Training (2019, methodology): “[35] Serge Gratton, Clément W Royer, Luís N Vicente, and Zaikun Zhang.”