Results 31 to 40 of about 252 (217)
Ensemble estimation of multivariate f-divergence [PDF]
2014 IEEE International Symposium on Information Theory, 2014 f-divergence estimation is an important problem in the fields of information theory, machine learning, and statistics. While several divergence estimators exist, relatively few of their convergence rates are known. We derive the MSE convergence rate for a density plug-in estimator of f-divergence.
Kevin R. Moon, Alfred O. Hero III
openaire +2 more sources
Remote Sensing, 2023 The accurate detection of collapsed buildings is of great significance for post-disaster rescue and reconstruction. High-resolution optical images are important data sources for identifying collapsed buildings, and the identification accuracy mainly ...
Ruoyang Liu, Wenquan Zhu, Xinyi Yang
doaj +1 more source
On Relativistic $f$-Divergences
CoRR, 2019 This paper provides a more rigorous look at Relativistic Generative Adversarial Networks (RGANs). We prove that the objective function of the discriminator is a statistical divergence for any concave function $f$ with minimal properties ($f(0)=0$, $f'(0) \neq 0$, $\sup_x f(x)>0$).
openaire +3 more sources
Law invariant risk measures and information divergences
Dependence Modeling, 2018 Aone-to-one correspondence is drawnbetween lawinvariant risk measures and divergences,which we define as functionals of pairs of probability measures on arbitrary standard Borel spaces satisfying a few natural properties.
Lacker Daniel
doaj +1 more source
On Data-Processing and Majorization Inequalities for f-Divergences with Applications
Entropy, 2019 This paper is focused on the derivation of data-processing and majorization inequalities for f-divergences, and their applications in information theory and statistics.
Igal Sason
doaj +1 more source
Nonperturbative negative geometries: amplitudes at strong coupling and the amplituhedron
Journal of High Energy Physics, 2022 The amplituhedron determines scattering amplitudes in planar N $$ \mathcal{N} $$ = 4 super Yang-Mills by a single “positive geometry” in the space of kinematic and loop variables.
Nima Arkani-Hamed +2 more
doaj +1 more source
EntropyTwo typical fixed-length random number generation problems in information theory are considered for general sources. One is the source resolvability problem and the other is the intrinsic randomness problem.
Ryo Nomura, Hideki Yagi
doaj +1 more source
About the sharpness of the Jensen inequality
Journal of Inequalities and Applications, 2018 The main aim of this paper is to give an improvement of the recent result on the sharpness of the Jensen inequality. The results given here are obtained using different Green functions and considering the case of the real Stieltjes measure, not ...
Ðilda Pečarić +2 more
doaj +1 more source
f-Divergence constrained policy improvement [PDF]
CoRR, 2017 To ensure stability of learning, state-of-the-art generalized policy iteration algorithms augment the policy improvement step with a trust region constraint bounding the information loss. The size of the trust region is commonly determined by the Kullback-Leibler (KL) divergence, which not only captures the notion of distance well but also yields ...
Belousov, Boris, Peters, Jan
openaire +2 more sources
Pediatric Blood &Cancer, EarlyView.ABSTRACT Pediatric gastroenteropancreatic neuroendocrine neoplasms (GEP‐NENs) are extremely rare and clinically heterogeneous. Management has largely been extrapolated from adult practice. This European Standard Clinical Practice Guideline (ESCP), developed by the EXPeRT network in collaboration with adult NEN experts, provides (adult) evidence ...
Michaela Kuhlen +23 more
wiley +1 more source