Logistic Regression, AdaBoost and Bregman Distances

By Michael Collins, Robert E. Schapire, Yoram Singer. Machine-mediated learning, 2000

749 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/b54c9359e8858842d1b1b744ac5ca573b8031dcc

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 Computer Vision and Pattern Recognition

Citations in the corpus

Tikhonov, Ivanov and Morozov regularization for support vector machine learning (2016, background): “…· Morozov regularization · Support vector machine B Luca Oneto Luca.Oneto@unige.it Sandro Ridella Sandro.Ridella@unige.it Davide Anguita Davide.Anguita@unige.it 1 DITEN - University of Genoa, Via Opera Pia 11a, 16145 Genoa, Italy 2 DIBRIS - University of Genoa, Via Opera Pia 13, 16145 Genoa, Italy”
On the Dual Formulation of Boosting Algorithms (2009, background): “Note that AdaBoost does not take the number of examples in each class into consideration when it models the problem.”
Automated trading with boosting and expert weighting (2010, positive): “…be predicted, x i corresponds to the features of an instance i , w ti is the weight of instance i at time t , h t and F t ( x ) are the prediction rule and the prediction score at time t respectively lowed by Collins, Schapire, and Singer [17] suggested a modiﬁcation of Adaboost, called Logitboost.”
Exploiting discriminant information in nonnegative matrix factorization with application to frontal face verification (2006, methodology): “More details about optimization algorithms using Bregman distances and KL dive rgence with linear constraints can be found in [35].”
Convexity, Classification, and Risk Bounds (2006, methodology): “Many of the most prominent methods studied in machine learning make significant use of convexity; in particular, support vector machines (Boser et al., 1992, Cortes and Vapnik, 1995, Cristianini and Shawe-Taylor, 2000, Sch¨olkopf and Smola, 2002), boosting (Freund and Schapire, 1997, Collins et al.”
Learning low dimensional word based linear classifiers using Data Shared Adaptive Bootstrap Aggregated Lasso with application to IMDb data (2018, background): “For further information about classical generalized linear model and it’s nonparametric version we refer to ( [1], [8]).”
One Trillion Edges: Graph Processing at Facebook-Scale (2015, methodology): “The BSP computing model also appears to be a good ﬁt for AdaBoost logistic regression from Collins et al. [16].”
An Introduction to Boosting and Leveraging (2002, methodology): “We demonstrate the convergence of ensemble learning methods such as AdaBoost [70] and Logistic Regression (LR) [74, 39], although the techniques are much more general.”
Boundary Detection Using F-Measure-, Filter- and Feature- (F3) Boost (2010, methodology): “For instance c(f(Xi), yi) = exp(−yif(Xi)) gives the exponential loss used in Adaboost training [18], while logistic regression scores have been considered in [19].”
Using EHRs and Machine Learning for Heart Failure Survival Analysis (2015, methodology): “The following classification algorithms were used: random forest [10], logistic regression [11,12], support vector regression [13], decision tree [14] and ada boost [15].”
On the equivalence of weak learnability and linear separability: new relaxations and efficient boosting algorithms (2010, methodology): “The LogLoss Boost algorithm (Collins et al. 2002) tries to minimize the cumulative logistic loss, which is less sensitive to noise.”