Results 11 to 20 of about 19,429 (283)
Dimension-Free Empirical Entropy Estimation
IEEE Transactions on Information Theory, 2023 We seek an entropy estimator for discrete distributions with fully empirical accuracy bounds. As stated, this goal is infeasible without some prior assumptions on the distribution. We discover that a certain information moment assumption renders the problem feasible. We argue that the moment assumption is natural and, in some sense, {\em minimalistic} -
Doron Cohen 0002 +3 more
openaire +3 more sources
Chernoff-Type Concentration of Empirical Probabilities in Relative Entropy [PDF]
IEEE Transactions on Information Theory, 2021 corrected a numerical ...
F. Richard Guo +1 more
openaire +2 more sources
Empirical entropy, minimax regret and minimax risk [PDF]
Bernoulli, 2017 We consider the random design regression model with square loss. We propose a method that aggregates empirical minimizers (ERM) over appropriately chosen random subsets and reduces to ERM in the extreme case, and we establish sharp oracle inequalities for its risk. We show that, under the $\varepsilon^{-p}$ growth of the empirical $\varepsilon$-entropy,
Rakhlin, Alexander +2 more
openaire +4 more sources
Convergence of Smoothed Empirical Measures With Applications to Entropy Estimation [PDF]
IEEE Transactions on Information Theory, 2020 This paper studies convergence of empirical measures smoothed by a Gaussian kernel. Specifically, consider approximating $P\ast\mathcal{N}_σ$, for $\mathcal{N}_σ\triangleq\mathcal{N}(0,σ^2 \mathrm{I}_d)$, by $\hat{P}_n\ast\mathcal{N}_σ$, where $\hat{P}_n$ is the empirical measure, under different statistical distances.
Ziv Goldfeld +3 more
openaire +3 more sources
Entropy conditions for L r -convergence of empirical processes [PDF]
Advances in Computational Mathematics, 2008 Let \(P_n\) be the empirical measure for a sample of \(n\) independent random elements with joint distribution \(P\). Furthermore, let \({\mathcal F}\) be a class of real-valued (bounded) functions defined on the sample space. Then it is known that \(\sup_{f\in {\mathcal F}}|P_nf - Pf| \to 0\) almost surely provided that \({\mathcal F}\) admits a ...
Andrea Caponnetto +2 more
openaire +1 more source
Entropy Generation through Deterministic Spiral Structures in a Corner Boundary-Layer Flow
Entropy, 2015 It is shown that nonlinear interactions between boundary layers on adjacent corner surfaces produce deterministic stream wise spiral structures. The synchronization properties of nonlinear spectral velocity equations of Lorenz form yield clearly defined ...
LaVar King Isaacson
doaj +1 more source
Entropy-based analysis and bioinformatics-inspired integration of global economic information transfer. [PDF]
PLoS ONE, 2013 The assessment of information transfer in the global economic network helps to understand the current environment and the outlook of an economy. Most approaches on global networks extract information transfer based mainly on a single variable. This paper
Jinkyu Kim +4 more
doaj +1 more source
Entropy, 2022 The vapor pressures of six solid 5-X-1,10-phenanthrolines (where X = Cl, CH3, CN, OCH3, NH2, NO2) were determined in suitable temperature ranges by Knudsen Effusion Mass Loss (KEML).
Bruno Brunetti +6 more
doaj +1 more source
Entropy, 2016 Results are presented for an innovative computational procedure that predicts time-dependent instabilities and deterministic ordered structures in three-dimensional steady-state laminar boundary-layer flows.
LaVar King Isaacson
doaj +1 more source
Data, 2023 In this article, we pioneer a new Burr X distribution using the odd beta prime generalized (OBP-G) family of distributions called the OBP-Burr X (OBPBX) distribution.
Ahmad Abubakar Suleiman +4 more
doaj +1 more source