• Publications
  • Influence
Algorithms for Hyper-Parameter Optimization
This work contributes novel techniques for making response surface models P(y|x) in which many elements of hyper-parameter assignment (x) are known to be irrelevant given particular values of other elements.
Learning and Design of Principal Curves
This work defines principal curves as continuous curves of a given length which minimize the expected squared distance between the curve and points of the space randomly chosen according to a given distribution, making it possible to theoretically analyze principal curve learning from training data and it also leads to a new practical construction.
Collaborative hyperparameter tuning
A generic method to incorporate knowledge from previous experiments when simultaneously tuning a learning algorithm on new problems at hand is proposed and is demonstrated in two experiments where it outperforms standard tuning techniques and single-problem surrogate-based optimization.
Aggregate features and ADABOOST for music classification
An algorithm that predicts musical genre and artist from an audio waveform using the ensemble learner ADABOOST and evidence collected from a variety of popular features and classifiers that the technique of classifying features aggregated over segments of audio is better than classifying either entire songs or individual short-timescale features.
Correlation of the highest-energy cosmic rays with nearby extragalactic objects.
Using data collected at the Pierre Auger Observatory during the past 3.7 years, we demonstrated a correlation between the arrival directions of cosmic rays with energy above 6 x 10(19) electron volts
Observation of the suppression of the flux of cosmic rays above 4 x 10 (19) eV.
The energy spectrum of cosmic rays above 2.5 x 10;{18} eV, derived from 20,000 events recorded at the Pierre Auger Observatory, is described and the hypothesis of a single power law is rejected with a significance greater than 6 standard deviations.
Principal curves: learning, design, and applications
The main result here is the first known consistency proof of a principal curve estimation scheme, and an application of the polygonal line algorithm to hand-written character skeletonization.
Piecewise Linear Skeletonization Using Principal Curves
The results indicated that the proposed algorithm can find a smooth medial axis in the great majority of a wide variety of character templates and that it substantially improves the pixel-wise skeleton obtained by traditional thinning methods.