174 citations · 991 across the 46 of their papers we have counts for
4 papers · 1 filter
Moment-based Uniform Deviation Bounds for -means and Friends
Matus Telgarsky, Sanjoy Dasgupta
Suppose centers are fit to points by heuristically minimizing the -means cost; what is the corresponding fit over the source distribution? This question is resolved here…
Boosting with the Logistic Loss is Consistent
Matus Telgarsky
This manuscript provides optimization guarantees, generalization bounds, and statistical consistency results for AdaBoost variants which replace the exponential loss with the logis…
Margins, Shrinkage, and Boosting
Matus Telgarsky
This manuscript shows that AdaBoost and its immediate variants can produce approximate maximum margin classifiers simply by scaling step size choices with a fixed small constant. I…
Dirichlet draws are sparse with high probability
Matus Telgarsky
This note provides an elementary proof of the folklore fact that draws from a Dirichlet distribution (with parameters less than 1) are typically sparse (most coordinates are small)…