SUBjektivApr 15, 2024

15.04.2024

1. DER MODERNE MAN - sinnlos
2. SILICON VALUE - bystander apathy
3. EINSTÜRZENDE NEUNAUTEN - Sehnsucht
4. THE LIPSCHITZ - ventilator
5. THE CREATURES - ice house
6. SPACED - downfall
7. GRAUZONE - der Weg zu zweit
8. CEL RAY - piss park
9. ONYON -

https://www.subjektiv.net/15-04-2024/

#2024 #CATVALLEY #CELRAY #CREATURES #DERMODERNEMAN #EINSTRZENDENEUBAUTEN #FALL #GRAUZONE #LIPSCHITZ #ONYON #SANTRRAOXYD #SILICONVALUE #SPACED #SWEEPINGPROMISES #TOMBEAU #TOXOPLASMA

15.04.2024 – SUBjektiv

JMLRApr 15, 2024

'Improving Lipschitz-Constrained Neural Networks by Learning Activation Functions', by Stanislas Ducotterd et al.

http://jmlr.org/papers/v25/22-1347.html

#regularization #optimization #lipschitz

Improving Lipschitz-Constrained Neural Networks by Learning Activation Functions

JMLRJan 5, 2024

'Limitations on approximation by deep and shallow neural networks', by Guergana Petrova, Przemyslaw Wojtaszczyk.

http://jmlr.org/papers/v24/22-1381.html

#approximation #lipschitz #approximants

Limitations on approximation by deep and shallow neural networks

JMLRMay 5, 2023

'Sparse Training with Lipschitz Continuous Loss Functions and a Weighted Group L0-norm Constraint', by Michael R. Metel.

http://jmlr.org/papers/v24/22-0615.html

#sparse #minimizing #lipschitz

Sparse Training with Lipschitz Continuous Loss Functions and a Weighted Group L0-norm Constraint

xameerJul 25, 2021
Suppose  f  is uniformly #Lipschitz continuous in y (meaning the Lipschitz constant can be taken independent of t) and continuous in t, then for some value ε > 0, there exists a unique solution y(t) to the initial value problem on the interval [t_0- ε,t_0+ε ]}
xameerDec 14, 2020
Contd these algorithms can be generalized to value-measures that are #Lipschitz continuous. Since such functions can be approximated as piecewise-constant functions "as close as we like", the above algorithms can also approximate a PEEF allocation "as close as we like"
xameerDec 14, 2020
Contd these algorithms can be generalized to value-measures that are #Lipschitz continuous. Since such functions can be approximated as piecewise-constant functions "as close as we like", the above algorithms can also approximate a PEEF allocation "as close as we like"
xameerNov 24, 2020
Suppose  f  is uniformly Lipschitz continuous in y (meaning #Lipschitz constant can be taken independent of t) and continuous in t, then for some value ε > 0, there exists a unique solution y(t) to the ivp on interval { [t_{0}-\varepsilon ,t_{0}+\varepsilon ]}
xameerNov 24, 2020
Suppose  f  is uniformly Lipschitz continuous in y (meaning #Lipschitz constant can be taken independent of t) and continuous in t, then for some value ε > 0, there exists a unique solution y(t) to the ivp on interval { [t_{0}-\varepsilon ,t_{0}+\varepsilon ]}
xameerNov 21, 2020
metric differential is a generalization of a derivative for a #Lipschitz continuous function defined on a Euclidean space and taking values in an arbitrary metric space.