ABSTRACT. Estimating a non-uniformly sampled function from a set of learning points is a classical regression problem. Kernel methods have been widely used in this context, but eve...
The Vapnik-Chervonenkis (V-C) dimension is an important combinatorial tool in the analysis of learning problems in the PAC framework. For polynomial learnability, we seek upper bou...
A multitask learning framework is developed for discriminative classification and regression where multiple large-margin linear classifiers are estimated for different predictio...
ys when planning meant searching for a sequence of abstract actions that satisfied some symbolic predicate. Robots can now learn their own representations through statistical infe...
In this paper we introduce a framework for privacypreserving distributed computation that is practical for many real-world applications. The framework is called Peers for Privacy ...
Yitao Duan, NetEase Youdao, John Canny, Justin Z. ...