Open AccessBook
An Introduction to Computational Learning Theory
Michael Kearns,Umesh Vazirani +1 more
Reads0
Chats0
TLDR
The probably approximately correct learning model Occam's razor the Vapnik-Chervonenkis dimension weak and strong learning learning in the presence of noise inherent unpredictability reducibility in PAC learning learning finite automata is described.Abstract:
The probably approximately correct learning model Occam's razor the Vapnik-Chervonenkis dimension weak and strong learning learning in the presence of noise inherent unpredictability reducibility in PAC learning learning finite automata by experimentation appendix - some tools for probabilistic analysis.read more
Citations
More filters
Posted ContentDOI
Quantum de Finetti Theorems under Local Measurements with Applications
TL;DR: Two new quantum de Finetti theorems are proved, both showing that under tests formed by local measurements one can get a much improved error dependence on the dimension of the subsystems, and a quasipolynomial-time algorithm for deciding multipartite separability is found.
Posted Content
Predicting the expected behavior of agents that learn about agents: the CLRI framework
José M. Vidal,Edmund H. Durfee +1 more
TL;DR: A framework and equations used to model and predict the behavior of multi-agent systems (MASs) with learning agents, and uses PAC-theory to show how to calculate bounds on the values of the learning parameters.
Proceedings Article
Stochastic local search in k-term DNF learning
Ulrich Rückert,Stefan Kramer +1 more
TL;DR: In this paper, a native stochastic local search algorithm for solving k-term DNF problems is presented, which is evaluated on hard K-term problems that lie on the phase transition and compared to the performance of GSAT and WalkSAT type algorithms.
Proceedings Article
Stratified sampling meets machine learning
TL;DR: An efficient and simple regularized Empirical Risk Minimization (ERM) algorithm along with a theoretical generalization result that significantly improve over both uniform sampling and standard stratified sampling which are de-facto the industry standards.
Journal ArticleDOI
Burst Load Evacuation Based on Dispatching and Scheduling In Distributed Edge Networks
TL;DR: In this paper, the authors proposed a load evacuation strategy for edge computing environments, where the number of service requests for mobile devices or IoT devices increases rapidly within a short period of time.