In 2014, Amin, Heidari, and Kearns proved that tree networks can be learned by observing only the infected set of vertices of the contagion process under the independent cascade model, in both the active and passive query models. They also showed empirically that simple extensions of their algorithms work on sparse networks. In this work, we focus on the active model. We prove that a simple mod...

We prove strong noise-tolerance properties of a potential-based boosting algorithm, similar to MadaBoost (Domingo and Watanabe, 2000) and SmoothBoost (Servedio, 2003). Our analysis is in the agnostic framework of Kearns, Schapire and Sellie (1994), giving polynomial-time guarantees in presence of arbitrary noise. A remarkable feature of our algorithm is that it can be implemented without reweig...

A. M. Kearns (correspondence) and M. C. Double, Div. of Botany and Zoology, Australian National University, Canberra, ACT 0200, Australia. E-mail: [email protected]. L. Joseph, Australian National Wildlife Collection, CSIRO Sustainable Ecosystems, GPO Box 284, Canberra, ACT 2601, Australia. S. V. Edwards, Dept. of Organismic and Evolutionary Biology, Museum of Comparative Zoology, Harvard Univ...

Soumen Basak, Hana Kim, Jeffrey D. Kearns, Vinay Tergaonkar, Ellen O’Dea, Shannon L. Werner, Chris A. Benedict, Carl F. Ware, Gourisankar Ghosh, Inder M. Verma, and Alexander Hoffmann* Department of Chemistry and Biochemistry Signaling Systems Laboratory University of California, San Diego, 9500 Gilman Drive, La Jolla, CA 92093, USA Laboratory of Genetics, Salk Institute for Biological Studies,...

We present metric, a provably near-optimal algorithm for reinforcement learning in Markov decision processes in which there is a natural metric on the state space that allows the construction of accurate local models. The algorithm is a generalization of the algorithm of Kearns and Singh, and assumes a black box for approximate planning. Unlike the original , metricfinds a near optimal policy i...

We provide a provably efficient algorithm for learning Markov Decision Processes (MDPs) with continuous state and action spaces in the online setting. Specifically, we take a model-based approach and show that a special type of online linear regression allows us to learn MDPs with (possibly kernalized) linearly parameterized dynamics. This result builds on Kearns and Singh’s work that provides ...

1 2 Colleen R. Courtney, Loralyn M. Cozy, and Daniel B. Kearns* 3 4 Indiana University 5 Department of Biology 6 Bloomington, IN 47408 7 8 Current address: 9 New York University 10 Sackler Institute of Microbiology-Parasitology 11 New York, NY 10016 12 13 Current address: 14 University of Hawaii 15 Department of Microbiology 16 Honolulu, HI 96822 17 18 19 Corresponding author 20 Email: dbkearns...

A case of mitochondrial myopathy and lactic acidaemia with myoclonic epilepsy, cerebellar ataxia and high-tone hearing loss is presented. There was no ptosis or ophthalmoplegia. Endocrine investigations showed a defect in hypothalamic function which was a likely cause of infertility. The case is compared with previously reported examples of mitochondrial myopathy with myoclonic epilepsy, and co...