Fábio C. C. Meneghetti

Fábio C. C. Meneghetti
University of Campinas | UNICAMP · Departamento de Matemática (DM)

Master of Science

About

7
Publications
240
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
0
Citations
Citations since 2017
6 Research Items
0 Citations
20172018201920202021202220230123456
20172018201920202021202220230123456
20172018201920202021202220230123456
20172018201920202021202220230123456
Introduction
Education
March 2018 - February 2020
University of Campinas
Field of study
  • Mathematics
March 2014 - February 2018
University of Campinas
Field of study
  • Mathematics

Publications

Publications (7)
Conference Paper
Full-text available
A full-rank lattice in the Euclidean space is a discrete set formed by all integer linear combinations of a basis. Given a probability distribution on Rn, two operations can be induced by considering the quotient of the space by such a lattice: wrapping and quantization. For a lattice Λ, and a fundamental domain D, which tiles Rn through Λ, the wra...
Article
Full-text available
Choosing a suitable loss function is essential when learning by empirical risk minimisation. In many practical cases, the datasets used for training a classifier may contain incorrect labels, which prompts the interest for using loss functions that are inherently robust to label noise. In this paper, we study the Fisher–Rao loss function, which eme...
Preprint
Full-text available
A full-rank lattice in the Euclidean space is a discrete set formed by all integer linear combinations of a basis. Given a probability distribution on $\mathbb{R}^n$, two operations can be induced by considering the quotient of the space by such a lattice: wrapping and quantization. For a lattice $\Lambda$, and a fundamental domain $D$ which tiles...
Preprint
Full-text available
Choosing a suitable loss function is essential when learning by empirical risk minimisation. In many practical cases, the datasets used for training a classifier may contain incorrect labels, which prompts the interest for using loss functions that are inherently robust to label noise. In this paper, we study the Fisher-Rao loss function, which eme...
Presentation
Full-text available
We study the Fisher-Rao loss function, which emerges from the Fisher-Rao distance in the statistical manifold of discrete distributions, especially in the presence of label noise.

Network

Projects

Projects (2)
Project
We investigate properties of wrapping and quantization of random variables with respect to lattices, with particular focus to information-theoretic aspects. Potential applications are dithering, uniform vector quantization, post-quantum cryptography and statistics.
Project
To study information-geometric techniques and their applications to problems in signal processing and machine learning.