On the Convergence of Leveraging

By Gunnar Rätsch, Sebastian Mika, Manfred K. Warmuth. 2001

47 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

AdaNet: Adaptive Structural Learning of Artificial Neural Networks (2016, methodology): “As in regularized boosting style methods (e.g. [Rätsch et al., 2001]), our algorithm will apply coordinate descent to the following objective function over R N : where Γ j = λr j + β with λ ≥ 0 and β ≥ 0 hyperparameters.”
Unifying Divergence Minimization and Statistical Inference Via Convex Duality (2006, background): “When the dual is a finite program, it is possible to achieve linear convergence rates (where the difference in Equation 18 goes exponentially fast to 0 in k) [17].”
Coordinate Descent Converges Faster with the Gauss-Southwell Rule Than Random Selection (2015, methodology): “This rule has been used in the context of boosting [R¨atsch et al., 2001], graphical models [Della Pietra et al., 1997, Lee et al., 2006, Scheinberg and Rish, 2009], Gaussian processes [Bo and Sminchisescu, 2008], and low-rank tensor approximations [Li et al., 2015].”
An Introduction to Boosting and Leveraging (2002, background): “Later we will show in Sections 4 and 5 that this relates to barrier optimization techniques [156] and coordinate descent methods [197, 151].”
Deep Boosting (2014, methodology): “…exponential loss), to Logistic Regression ( = = 0 with logistic loss), which we abbreviate as LogReg, to L 1 -norm regularized AdaBoost (e.g., see (Rätsch et al., 2001a)) abbreviated as AdaBoost-L1, and also to the L 1 -norm regularized additive Logistic Regression algorithm studied by (Duchi &…”
Multi-Class Deep Boosting (2014, background): “And indeed, overfitting has been reported in practice for AdaBoost in the past [Grove and Schuurmans, 1998, Schapire, 1999, Dietterich, 2000, Rätsch et al., 2001b].”