The standard design of control systems is based on the periodic sampling. Every period the data is read from the input, the control law is computed, and the output is written to t...
We summarize the results of an experimental performance evaluation of using an empirical histogram to approximate the steady-state distribution of the underlying stochastic proces...
When only a small number of labeled samples are available, supervised dimensionality reduction methods tend to perform poorly due to overfitting. In such cases, unlabeled samples ...
We describe and explore a new perspective on the sample complexity of active learning. In many situations where it was generally believed that active learning does not help, we sh...
Maria-Florina Balcan, Steve Hanneke, Jennifer Wort...
The focus of this paper is on how to select a small sample of examples for labeling that can help us to evaluate many different classification models unknown at the time of sampl...