In machine learning theory, problem classes are distinguished because of di erences in complexity. In 6 , a stochastic model of learning from examples was introduced. This PAClear...
We consider a variety of connections between threshold graphs, shifted complexes, and simplicial complexes naturally formed from a graph. These graphical complexes include the inde...
We extend Lutz's resource-bounded measure to probabilistic classes, and obtain notions of resource-bounded measure on probabilistic complexity classes such as BPE and BPEXP. ...
Model selection in unsupervised learning is a hard problem. In this paper a simple selection criterion for hyperparameters in one-class classifiers (OCCs) is proposed. It makes us...
We introduce a large self-dual class of simplicial complexes for which we show that each member complex is contractible or homotopy equivalent to a sphere. Examples of complexes i...