-Divergence Based Classification: Beyond the Use of Cross-Entropy
N Novello, AM Tonello - arXiv preprint arXiv:2401.01268, 2024 - arxiv.org
In deep learning, classification tasks are formalized as optimization problems solved via the
minimization of the cross-entropy. However, recent advancements in the design of objective …
minimization of the cross-entropy. However, recent advancements in the design of objective …
Data-Driven Estimation of the False Positive Rate of the Bayes Binary Classifier via Soft Labels
Classification is a fundamental task in many applications on which data-driven methods
have shown outstanding performances. However, it is challenging to determine whether …
have shown outstanding performances. However, it is challenging to determine whether …
Data Permutation Recovery from Noisy Data: Error Probability and Privacy
M Jeong - 2024 - search.proquest.com
This doctoral thesis investigates the data permutation recovery problem from noisy
observations, a fundamental challenge at the intersection of data science and privacy …
observations, a fundamental challenge at the intersection of data science and privacy …