Algorithmic Probability-Guided Machine Learning on Non-Differentiable Spaces

Algorithmic Aspects of Machine Learning

Acceptable random variables in non-commutative probability spaces

Acceptable random variables are defined in noncommutative (quantum) probability spaces and some of probability inequalities for these classes  are obtained. These results are a generalization of negatively orthant dependent random variables in probability theory. Furthermore, the obtained results can be used for random matrices.

A System for Incremental Learning Based on Algorithmic Probability

We have employed Algorithmic Probability Theory to construct a system for machine learning of great power and generality. The principal thrust of present research is the design of sequences of problems to train

Algorithmic Shearer ’ s Lemma for general probability spaces

In the last two lectures we presented an algorithmic proof of the LLL (and in fact Shearer’s lemma) when the underlying probability space consists of independent random variables. In this lecture we present an “algorithmic proof” of Shearer’s Lemma for a general probability space. We note that the first abstract algorithmic framework for the LLL beyond [Moser and Tardos (2010)] was proposed by ...

The Great Ray Solomonoff, pioneer of Machine Learning, founder of Algorithmic Probability

Satisfiability (SAT) testing methods have been usedeffectively in many inference, planning and constraintsatisfaction tasks and thus have been considered acontribution towards artificial general intelligence.However, since SAT constraints are defined over atomicpropositions, domains with state variables that change overtime can lead to extremely large search spaces. This...