Corrections to “Generalization Bounds via Information Density and Conditional Information Density”
نویسندگان
چکیده
An error in the proof of data-dependent tail bounds on generalization presented Hellström and Durisi (2020) is identified, a correction proposed. Furthermore, we note that absolute continuity requirements need to be strengthened avoid measurability issues.
منابع مشابه
Separability of Density Matrices and Conditional Information Transmission
We give necessary and sufficient conditions under which a density matrix acting on a two-fold tensor product space is separable. Our conditions are given in terms of quantum conditional information transmission.
متن کاملConditional Density Estimation via Least-Squares Density Ratio Estimation
Estimating the conditional mean of an inputoutput relation is the goal of regression. However, regression analysis is not sufficiently informative if the conditional distribution has multi-modality, is highly asymmetric, or contains heteroscedastic noise. In such scenarios, estimating the conditional distribution itself would be more useful. In this paper, we propose a novel method of condition...
متن کاملConsistency and Generalization Bounds for Maximum Entropy Density Estimation
We investigate the statistical properties of maximum entropy density estimation, both for the complete data case and the incomplete data case. We show that under certain assumptions, the generalization error can be bounded in terms of the complexity of the underlying feature functions. This allows us to establish the universal consistency of maximum entropy density estimation.
متن کاملInformation Geometric Density Estimation
We investigate kernel density estimation where the kernel function varies from point to point. Density estimation in the input space means to find a set of coordinates on a statistical manifold. This novel perspective helps to combine efforts from information geometry and machine learning to spawn a family of density estimators. We present example models with simulations. We discuss the princip...
متن کاملInformation Density and Syntactic Repetition
In noun phrase (NP) coordinate constructions (e.g., NP and NP), there is a strong tendency for the syntactic structure of the second conjunct to match that of the first; the second conjunct in such constructions is therefore low in syntactic information. The theory of uniform information density predicts that low-information syntactic constructions will be counterbalanced by high information in...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE journal on selected areas in information theory
سال: 2021
ISSN: ['2641-8770']
DOI: https://doi.org/10.1109/jsait.2021.3088240