Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- California Institute of TechnologyUS2.6k papers
- Massachusetts Institute of TechnologyUS2.2k papers
- Centre National de la Recherche ScientifiqueFR2.2k papers
- University of California, Santa BarbaraUS2.1k papers
- The Ohio State UniversityUS2k papers
- University of California, Los AngelesUS2k papers
- Princeton UniversityUS1.9k papers
- University of Wisconsin–MadisonUS1.9k papers
- Johns Hopkins UniversityUS1.8k papers
- University of Colorado BoulderUS1.8k papers
- University of California, RiversideUS1.7k papers
- Purdue University West LafayetteUS1.7k papers
5 papers · 2 filters
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…
Classifying Single-Trial EEG during Motor Imagery with a Small Training Set
Yijun Wang
Before the operation of a motor imagery based brain-computer interface (BCI) adopting machine learning techniques, a cumbersome training procedure is unavoidable. The development o…
Understanding ACT-R - an Outsider's Perspective
Jacob Whitehill
The ACT-R theory of cognition developed by John Anderson and colleagues endeavors to explain how humans recall chunks of information and how they solve problems. ACT-R also serves…
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…