21 citations · 33 across the 4 of their papers we have counts for
5 papers
On Closed-Form Expressions for the Fisher-Rao Distance
Henrique K. Miyamoto, Fábio C. C. Meneghetti, Julianna Pinele +1
The Fisher-Rao distance is the geodesic distance between probability distributions in a statistical manifold equipped with the Fisher metric, which is a natural choice of Riemannia…
The Fisher-Rao Loss for Learning under Label Noise
Henrique K. Miyamoto, Fábio C. C. Meneghetti, Sueli I. R. Costa
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 incorr…
Information Properties of a Random Variable Decomposition through Lattices
Fábio C. C. Meneghetti, Henrique K. Miyamoto, Sueli I. R. Costa
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 , two operation…
Context-Tree-Based Lossy Compression and Its Application to CSI Representation
Henrique K. Miyamoto, Sheng Yang
We propose novel compression algorithms for time-varying channel state information (CSI) in wireless communications. The proposed scheme combines (lossy) vector quantisation and (l…
Constructive Spherical Codes by Hopf Foliations
Henrique K. Miyamoto, Sueli I. R. Costa, Henrique N. Sá Earp
We present a new systematic approach to constructing spherical codes in dimensions , based on Hopf foliations. Using the fact that a sphere is foliated by manifolds…