Variational bounds on the diffusive and hydrodynamic permeabilities of randomly perforated sheets

Author(s):  
George H. Malone ◽  
Suk Youn Suh ◽  
Stephen Prager
2002 ◽  
Vol 68 (667) ◽  
pp. 428-433 ◽  
Author(s):  
Shigeru NAGAKI ◽  
Katsutoshi SUMIYOSHI ◽  
Katsuyuki ABE

2000 ◽  
Vol 63 (3) ◽  
pp. 353-364
Author(s):  
A. G. Donchev ◽  
N. N. Kolesnikov ◽  
V. I. Tarasov

2008 ◽  
Vol 79 (3) ◽  
pp. 189-204
Author(s):  
H. Brito-Santana ◽  
R. Rodríguez-Ramos ◽  
R. Guinovart-Díaz ◽  
J. Bravo-Castillero ◽  
F. J. Sabina ◽  
...  

1989 ◽  
Vol 3 (4) ◽  
pp. 286-288
Author(s):  
A I Kheifets ◽  
O A Denyachenko ◽  
S P Timchenko ◽  
L I Sedykh

Entropy ◽  
2020 ◽  
Vol 22 (11) ◽  
pp. 1229 ◽  
Author(s):  
Bernhard C. Geiger ◽  
Ian S. Fischer

In this short note, we relate the variational bounds proposed in Alemi et al. (2017) and Fischer (2020) for the information bottleneck (IB) and the conditional entropy bottleneck (CEB) functional, respectively. Although the two functionals were shown to be equivalent, it was empirically observed that optimizing bounds on the CEB functional achieves better generalization performance and adversarial robustness than optimizing those on the IB functional. This work tries to shed light on this issue by showing that, in the most general setting, no ordering can be established between these variational bounds, while such an ordering can be enforced by restricting the feasible sets over which the optimizations take place. The absence of such an ordering in the general setup suggests that the variational bound on the CEB functional is either more amenable to optimization or a relevant cost function for optimization in its own regard, i.e., without justification from the IB or CEB functionals.


Sign in / Sign up

Export Citation Format

Share Document