Projected Newton-type methods in machine learning

85 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Stochastic Polyak Step-size for SGD: An Adaptive Learning Rate for Fast Convergence (2020, methodology): “Furthermore, similar to (Schmidt et al., 2011), we propose a way to increase the mini-batch size for evaluating the stochastic gradient and guarantee convergence to the optimal solution without interpolation.”
Optimization with Sparsity-Inducing Penalties (2011, neutral): “, [72]).”
Convergence Analysis of Inexact Randomized Iterative Methods (2019, result): “chastic algorithms appears in the area of second order methods. In particular on inexact variants of the Sketch-Newton method and subsampled Newton Method for minimize convex and non-convex functions [48,2,4,56,57,58]. Note that our results are related also with this literature since our algorithm c”
Convergence Rates of Inexact Proximal-Gradient Methods for Convex Optimization (2011, background): “Finally, we note that there has been recent interest in inexact proximal Newton-like methods [40], and it would be interesting to analyze the effect of errors on the convergence rates of these methods.”
Randomized Iterative Methods for Linear Systems: Momentum, Inexactness and Gossip (2019, methodology): “In particular on inexact variants of the Sketch-Newton method and subsampled Newton Method for minimize convex and nonconvex functions [172, 9, 14, 204, 205, 207].”