Search Results for author:
Found 6 papers, 0 papers with code
Metastable Financial Markets
Metastability is a phenomenon observed in stochastic systems which stay in a false-equilibrium within a region of its state space until the occurrence of a sequence of rare events that leads to an abrupt transition to a different region.
The role of prior information and computational power in Machine Learning
Science consists on conceiving hypotheses, confronting them with empirical evidence, and keeping only hypotheses which have not yet been falsified.
Learning the hypotheses space from data through a U-curve algorithm
This paper proposes a data-driven systematic, consistent and non-exhaustive approach to Model Selection, that is an extension of the classical agnostic PAC learning model.
Learning the Hypotheses Space from data Part II: Convergence and Feasibility
In this paper, we carry further our agenda, by showing the consistency of a model selection framework based on Learning Spaces, in which one selects from data the Hypotheses Space on which to learn.
Learning the Hypotheses Space from data: Learning Space and U-curve Property
A remarkable, formally proved, consequence of this approach are conditions on $\mathbb{L}(\mathcal{H})$ and on the loss function that lead to estimated out-of-sample error surfaces which are true U-curves on $\mathbb{L}(\mathcal{H})$ chains, enabling a more efficient search on $\mathbb{L}(\mathcal{H})$.
Feature Selection based on the Local Lift Dependence Scale
The main contribution of this paper is to define and apply this local measure, which permits to analyse local properties of joint distributions that are neglected by the classical Shanon's global measure.
