research
∙
02/14/2023
On Classification-Calibration of Gamma-Phi Losses
Gamma-Phi losses constitute a family of multiclass classification loss f...
research
∙
05/19/2022
Consistent Interpolating Ensembles via the Manifold-Hilbert Kernel
Recent research in the theory of overparametrized learning has sought to...
research
∙
10/06/2021
VC dimension of partially quantized neural networks in the overparametrized regime
Vapnik-Chervonenkis (VC) theory has so far been unable to explain the sm...
research
∙
02/10/2021
An exact solver for the Weston-Watkins SVM subproblem
Recent empirical evidence suggests that the Weston-Watkins support vecto...
research
∙
06/12/2020
Weston-Watkins Hinge Loss and Ordered Partitions
Multiclass extensions of the support vector machine (SVM) have been form...
research
∙
06/30/2016
An Operator Theoretic Approach to Nonparametric Mixture Models
When estimating finite mixture models, it is common to make assumptions ...
research
∙
02/23/2015
On The Identifiability of Mixture Models from Grouped Samples
Finite mixture models are statistical models which appear in many proble...
research
∙
11/17/2014
Robust Kernel Density Estimation by Scaling and Projection in Hilbert Space
While robust parameter estimation has been well studied in parametric de...
research
∙
07/15/2011