no code implementations • 19 Oct 2023 • Diego Marcondes, Adilson Simonis
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.
no code implementations • 31 Oct 2022 • Diego Marcondes, Adilson Simonis, Junior Barrera
Science consists on conceiving hypotheses, confronting them with empirical evidence, and keeping only hypotheses which have not yet been falsified.
no code implementations • 8 Sep 2021 • Diego Marcondes, Adilson Simonis, Junior Barrera
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.
no code implementations • 30 Jan 2020 • Diego Marcondes, Adilson Simonis, Junior Barrera
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.
no code implementations • 26 Jan 2020 • Diego Marcondes, Adilson Simonis, Junior Barrera
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 $\mathbb{L}(\mathcal{H})$.
no code implementations • 11 Nov 2017 • Diego Marcondes, Adilson Simonis, Junior Barrera
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.