Bayesian optimization is obsolete

[Prove me wrong No.9448549]

https://arxiv.org/abs/1703.02628

[Anonymous No.9448628]

>>9448549
Can you give me a quick run down? How does this scale with number of dimensions?

[Anonymous No.9448721]

>>9448549
Nice try there brainlet. Arxiv is where the crackpot (((scientists))) post results that are complete nonsense. Vixra is where all the real scientific preprints are posted.

[Anonymous No.9448735]

>>9448549
Has been for decades, what's your point?

[Anonymous No.9450394]

>>9448549
Mark Wahlberg has three nipples.

[Anonymous No.9450467]

>>9448549
Notice how they conveniently leave out discussing sample efficiency or optimizer hyper-hyperparameter selection and only discuss which algorithm converged to a better optimum. Trash, just like most theory-heavy papers.

[Anonymous No.9450469]

>>9448735
What do you propose to replace it?

[Anonymous No.9450491]

How is this different from the algorithms which have been used in NLopt for years?

https://nlopt.readthedocs.io/en/latest/NLopt_Algorithms/#direct-and-direct-l

D. R. Jones, C. D. Perttunen, and B. E. Stuckmann, "Lipschitzian optimization without the lipschitz constant," J. Optimization Theory and Applications, vol. 79, p. 157 (1993).

J. M. Gablonsky and C. T. Kelley, "A locally-biased form of the DIRECT algorithm," J. Global Optimization, vol. 21 (1), p. 27-37 (2001).

[Anonymous No.9450897]

>>9450469
The methods we've been using for decades since the obsolescence of bayesian optimization, retard. Is google too hard for you too?

[Anonymous No.9450903]

>>9450897
But Bayesian optimization is the state of the art. Literally what did he mean by this?

t. optimization researcher

[Anonymous No.9452584]

>>9448549
>https://arxiv.org/abs/1703.02628
"Lipschitz"
fucking kek'd