Several of our current PhD candidates and fellow researchers at the Data Science Institute have published, or in the proccess of publishing, papers to present their research.
@inproceedings{Rosas:2021:10.1109/itw46852.2021.9457579,
author = {Rosas, FE and Mediano, PAM and Gastpar, M},
doi = {10.1109/itw46852.2021.9457579},
pages = {1--5},
publisher = {IEEE},
title = {Learning, compression, and leakage: Minimising classification error via meta-universal compression principles},
url = {http://dx.doi.org/10.1109/itw46852.2021.9457579},
year = {2021}
}
TY - CPAPER
AB - Learning and compression are driven by the common aim of identifying and exploiting statistical regularities in data, which opens the door for fertile collaboration between these areas. A promising group of compression techniques for learning scenarios is normalised maximum likelihood (NML) coding, which provides strong guarantees for compression of small datasets — in contrast with more popular estimators whose guarantees hold only in the asymptotic limit. Here we consider a NMLbased decision strategy for supervised classification problems, and show that it attains heuristic PAC learning when applied to a wide variety of models. Furthermore, we show that the misclassification rate of our method is upper bounded by the maximal leakage, a recently proposed metric to quantify the potential of data leakage in privacy-sensitive scenarios.
AU - Rosas,FE
AU - Mediano,PAM
AU - Gastpar,M
DO - 10.1109/itw46852.2021.9457579
EP - 5
PB - IEEE
PY - 2021///
SP - 1
TI - Learning, compression, and leakage: Minimising classification error via meta-universal compression principles
UR - http://dx.doi.org/10.1109/itw46852.2021.9457579
UR - https://ieeexplore.ieee.org/document/9457579
UR - http://hdl.handle.net/10044/1/90016
ER -