We present a new algorithm for learning a convex set in n-dimensional space given labeled examples drawn from any Gaussian distribution. The complexity of the algorithm is bounded ...
We study the learnability of sets in Rn under the Gaussian distribution, taking Gaussian surface area as the “complexity measure” of the sets being learned. Let CS denote the ...
Adam R. Klivans, Ryan O'Donnell, Rocco A. Servedio
We propose a learning method for gait synthesis from a sequence of shapes(frames) with the ability to extrapolate to novel data. It involves the application of PCA, first to redu...
Muayed Sattar Al-Huseiny, Sasan Mahmoodi, Mark Nix...
Confidence-weighted (CW) learning [6], an online learning method for linear classifiers, maintains a Gaussian distributions over weight vectors, with a covariance matrix that repr...
Abstract. The Gram matrix plays a central role in many kernel methods. Knowledge about the distribution of eigenvalues of the Gram matrix is useful for developing appropriate model...