Some Sufficient Conditions on an Arbitrary Class of Stochastic Processes for the Existence of a Predictor

DOI10.1007/978-3-540-87987-9_17zbMath1156.60312MaRDI QIDQ3529918

Daniil Ryabko

Publication date: 14 October 2008

Published in: Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL: https://hal.inria.fr/inria-00347706/file/pq_.pdf

Mathematics Subject Classification ID

60G25: Prediction theory (aspects of stochastic processes)

Related Items

Discrimination between B-processes is impossible, Dynamics of Bayesian updating with dependent data and misspecified models

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Prediction of random sequences and universal coding
• Coding of a source with unknown but ordered probabilities
• Universal artificial intelligence. Sequential decisions based on algorithmic probability.
• Predicting non-stationary processes
• Sample complexity for computational classification problems
• Merging of Opinions with Increasing Information
• Complexity-based induction systems: Comparisons and convergence theorems
• A general minimax result for relative entropy
• Asymptotic minimax regret for data compression, gambling, and prediction
• Bayesian Representation of Stochastic Processes under Learning: de Finetti Revisited
• An algorithm for computing the capacity of arbitrary discrete memoryless channels