RSS

Optimization

TagLast edit: 30 Sep 2020 19:18 UTC by Ruby

An optimization process is any kind of process that systematically comes up with solutions that are better than the solution used before. More technically, this kind of process moves the world into a specific and unexpected set of states by searching through a large search space, hitting small and low probability targets. When this process is gradually guided by some agent into some specific state, through searching specific targets, we can say it prefers that state.

The best way to exemplify an optimization process is through a simple example: Eliezer Yudkowsky suggests natural selection is such a process. Through an implicit preference – better replicators – natural selection searches all the genetic landscape space and hit small targets: efficient mutations.

Consider the human being. We are a highly complex object with a low probability to have been created by chance—natural selection, however, over millions of years, built up the infrastructure needed to build such a functioning body. This body, as well as other organisms, had the chance (was selected) to develop because it is in itself a rather efficient replicator suitable for the environment where it came up.

Or consider the famous chessplaying computer, Deep Blue. Outside of the narrow domain of selecting moves for chess games, it can’t do anything impressive: but as a chessplayer, it was massively more effective than virtually all humans. It has a high optimization power in the chess domain but almost none in any other field. Humans or evolution, on the other hand, are more domain-general optimization processes than Deep Blue, but that doesn’t mean they’re more effective at chess specifically. (Although note in what contexts this optimization process abstraction is useful and where it fails to be useful: it’s not obvious what it would mean for “evolution” to play chess, and yet it is useful to talk about the optimization power of natural selection, or of Deep Blue.)

Measuring Optimization Power

One way to think mathematically about optimization, like evidence, is in information-theoretic bits. The optimization power is the amount of surprise we would have in the result if there were no optimization process present. Therefore we take the base-two logarithm of the reciprocal of the probability of the result. A one-in-a-million solution (a solution so good relative to your preference ordering that it would take a million random tries to find something that good or better) can be said to have log_2(1,000,000) = 19.9 bits of optimization. Compared to a random configuration of matter, any artifact you see is going to be much more optimized than this. The math describes only laws and general principles for reasoning about optimization; as with probability theory, you oftentimes can’t apply the math directly.

Further Reading & References

See also

The ground of optimization

alexflint20 Jun 2020 0:38 UTC
166 points
72 comments27 min readLW link

Optimization

Eliezer Yudkowsky13 Sep 2008 16:00 UTC
36 points
45 comments5 min readLW link

Op­ti­miza­tion Amplifies

Scott Garrabrant27 Jun 2018 1:51 UTC
86 points
12 comments4 min readLW link

Mea­sur­ing Op­ti­miza­tion Power

Eliezer Yudkowsky27 Oct 2008 21:44 UTC
42 points
34 comments6 min readLW link

Selec­tion vs Control

abramdemski2 Jun 2019 7:01 UTC
127 points
25 comments11 min readLW link2 nominations2 reviews

Risks from Learned Op­ti­miza­tion: Introduction

31 May 2019 23:44 UTC
144 points
40 comments12 min readLW link3 nominations3 reviews

Good­hart’s Curse and Limi­ta­tions on AI Alignment

G Gordon Worley III19 Aug 2019 7:57 UTC
21 points
18 comments9 min readLW link

Thoughts and prob­lems with Eliezer’s mea­sure of op­ti­miza­tion power

Stuart_Armstrong8 Jun 2012 9:44 UTC
37 points
23 comments5 min readLW link

What is op­ti­miza­tion power, for­mally?

sbenthall18 Oct 2014 18:37 UTC
17 points
16 comments2 min readLW link

Math­e­mat­i­cal Mea­sures of Op­ti­miza­tion Power

Alex_Altair24 Nov 2012 10:55 UTC
7 points
16 comments5 min readLW link

Op­ti­miza­tion Provenance

Adele Lopez23 Aug 2019 20:08 UTC
38 points
5 comments5 min readLW link

Two senses of “op­ti­mizer”

Joar Skalse21 Aug 2019 16:02 UTC
30 points
41 comments3 min readLW link

The Op­ti­mizer’s Curse and How to Beat It

lukeprog16 Sep 2011 2:46 UTC
79 points
82 comments3 min readLW link

Is the term mesa op­ti­mizer too nar­row?

Matthew Barnett14 Dec 2019 23:20 UTC
37 points
21 comments1 min readLW link

Mesa-Op­ti­miz­ers vs “Steered Op­ti­miz­ers”

Steven Byrnes10 Jul 2020 16:49 UTC
40 points
5 comments8 min readLW link

Mesa-Op­ti­miz­ers and Over-op­ti­miza­tion Failure (Op­ti­miz­ing and Good­hart Effects, Clar­ify­ing Thoughts—Part 4)

Davidmanheim12 Aug 2019 8:07 UTC
15 points
3 comments4 min readLW link

The Credit As­sign­ment Problem

abramdemski8 Nov 2019 2:50 UTC
74 points
40 comments17 min readLW link2 nominations1 review

Bot­tle Caps Aren’t Optimisers

DanielFilan31 Aug 2018 18:30 UTC
71 points
21 comments3 min readLW link
(danielfilan.com)

Fake Op­ti­miza­tion Criteria

Eliezer Yudkowsky10 Nov 2007 0:10 UTC
54 points
20 comments3 min readLW link

Search ver­sus design

alexflint16 Aug 2020 16:53 UTC
83 points
39 comments36 min readLW link

The First World Takeover

Eliezer Yudkowsky19 Nov 2008 15:00 UTC
29 points
24 comments6 min readLW link

Life’s Story Continues

Eliezer Yudkowsky21 Nov 2008 23:05 UTC
20 points
18 comments5 min readLW link

Utility Max­i­miza­tion = De­scrip­tion Length Minimization

johnswentworth18 Feb 2021 18:04 UTC
148 points
35 comments5 min readLW link

Ap­pli­ca­tions for De­con­fus­ing Goal-Directedness

adamShimi8 Aug 2021 13:05 UTC
34 points
0 comments5 min readLW link

A new defi­ni­tion of “op­ti­mizer”

Chantiel9 Aug 2021 13:42 UTC
7 points
0 comments7 min readLW link

Mea­sure­ment, Op­ti­miza­tion, and Take-off Speed

jsteinhardt10 Sep 2021 19:30 UTC
47 points
4 comments13 min readLW link

De­grees of Freedom

sarahconstantin2 Apr 2019 21:10 UTC
102 points
31 comments11 min readLW link
(srconstantin.wordpress.com)

He­donic asymmetries

paulfchristiano26 Jan 2020 2:10 UTC
90 points
22 comments2 min readLW link
(sideways-view.com)

De­mons in Im­perfect Search

johnswentworth11 Feb 2020 20:25 UTC
84 points
21 comments3 min readLW link

Tes­sel­lat­ing Hills: a toy model for demons in im­perfect search

DaemonicSigil20 Feb 2020 0:12 UTC
74 points
15 comments2 min readLW link

Align­ing a toy model of optimization

paulfchristiano28 Jun 2019 20:23 UTC
52 points
26 comments3 min readLW link

Siren wor­lds and the per­ils of over-op­ti­mised search

Stuart_Armstrong7 Apr 2014 11:00 UTC
69 points
417 comments7 min readLW link

Worse Than Random

Eliezer Yudkowsky11 Nov 2008 19:01 UTC
40 points
102 comments12 min readLW link

Effi­cient Cross-Do­main Optimization

Eliezer Yudkowsky28 Oct 2008 16:33 UTC
37 points
37 comments5 min readLW link

Op­ti­miza­tion and the Singularity

Eliezer Yudkowsky23 Jun 2008 5:55 UTC
28 points
21 comments9 min readLW link

Ob­serv­ing Optimization

Eliezer Yudkowsky21 Nov 2008 5:39 UTC
9 points
28 comments6 min readLW link

Satis­ficers want to be­come maximisers

Stuart_Armstrong21 Oct 2011 16:27 UTC
31 points
68 comments1 min readLW link

Evolu­tions Build­ing Evolu­tions: Lay­ers of Gen­er­ate and Test

plex5 Feb 2021 18:21 UTC
11 points
1 comment6 min readLW link

Sur­pris­ing ex­am­ples of non-hu­man optimization

Jan_Rzymkowski14 Jun 2015 17:05 UTC
31 points
9 comments1 min readLW link

Ac­ci­den­tal Optimizers

aysajan22 Sep 2021 13:27 UTC
7 points
0 comments3 min readLW link
No comments.