Parallel Boosting with Momentum

By Indraneel Mukherjee, Kevin Robert Canini, Rafael M. Frongillo, Yoram Singer. 2013

35 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Mechanics

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 Computational Mechanics

Citations in the corpus

Distributed Coordinate Descent Method for Learning with Big Data (2013, background): “Further recent works on parallel coordinate descent include (Richtárik & Takáč, 2012b; Mukherjee et al., 2013; Fercoq, 2013; Tappenden et al., 2013a; Shalev-Shwartz & Zhang, 2013a).”
Parallel Coordinate Descent for the Adaboost Problem (2013, methodology): “[7] interpreted the fully parallel coordinate descent method as a gradient method and designed an accelerated algorithm using accelerated gradient.”
Accelerated Parallel Optimization Methods for Large Scale Machine Learning (2014, methodology): “Indeed, while our results show that FISTA is provably faster than BOOM, experiments in [11] show the opposite on unnormalized data.”
Exact and Inexact Subsampled Newton Methods for Optimization (2016, background): “Data Set Data Points N Variables d Reference MNIST 70000 784 [15] Covertype 581012 54 [4] Mushroom 8124 112 [16] Synthetic 10000 50 [18] CINA 16033 132 [25] Gisette 7000 5000 [14] Table 5.”
An investigation of Newton-Sketch and subsampled Newton methods (2017, methodology): “The synthetic data sets were generated randomly as described in [14].”
On optimal probabilities in stochastic coordinate descent methods (2013, methodology): “methods were considered in [2,19,21], and more recently in [1,5,6,12,13,25,27,28].”
Quartz: Randomized Dual Coordinate Ascent with Arbitrary Sampling (2015, methodology): “Another accelerated method, BOOM, was proposed in [17].”
A Stochastic Quasi-Newton Method for Large-Scale Optimization (2014, methodology): “We ﬁrst test our algorithm on a binary classiﬁcation problem using randomly generated training points, as described in [14].”
A variational perspective on accelerated methods in optimization (2016, background): “There have been generalizations to non-Euclidean optimization [26, 17] and higher-order algorithms [28, 6], and there have been numerous applications that further extend the reach of the idea [14, 13, 15, 22].”