Sign up to save your podcasts
Or
Share “Natural Latents: Latent Variables Stable Across Ontologies” by johnswentworth, David Lorell
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
“Natural Latents: Latent Variables Stable Across Ontologies” by johnswentworth, David Lorell
Audio note: this article contains 369 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in the episode description.
There's a details box here with the title "Background on where this post/paper came from". The box contents are omitted from this narration.This post is an overhaul of (and large improvement to) a paper we wrote about a year ago. The pdf version will hopefully be up on arxiv shortly, and we will link that from here once it's available. As of posting, this is probably the best first-stop mathematical intro to natural latents.
Abstract
Suppose two Bayesian agents each learn a generative model of the same environment. We will assume the two have converged on the predictive distribution (i.e. distribution over some observables in the environment), but may have different generative models containing different latent variables. Under [...]
---
Outline:
(00:52) Abstract
(01:42) Background
(04:12) The Math
(04:15) Setup & Objective
(07:05) Notation
(09:45) Foundational Concepts: Mediation, Redundancy & Naturality
(12:59) Core Theorems
(14:51) Naturality _\\implies_ Minimality Among Mediators
(15:59) Naturality _\\implies_ Maximality Among Redunds
(16:47) Isomorphism of Natural Latents
(17:14) Application To Translatability
(17:18) Motivating Question
(18:27) Guaranteed Translatability
(21:09) Natural Latents: Intuition & Examples
(21:24) When Do Natural Latents Exist? Some Intuition From The Exact Case
(23:11) Worked Quantitative Example of the Mediator Determines Redund Theorem
(26:54) Intuitive Examples of Natural Latents
(27:17) Ideal Gas
(28:22) Biased Die
(29:36) Timescale Separation In A Markov Chain
(30:24) Discussion & Conclusion
(33:56) Acknowledgements
(34:05) Appendices
(34:08) Graphical Notation and Some Rules for Graphical Proofs
(35:02) Frankenstein Rule
(37:39) Factorization Transfer
(39:15) Bookkeeping Rule
(40:03) The Dangly Bit Lemma
(41:09) Graphical Proofs
(41:18) Python Script for Computing _D_{KL}_ in Worked Example
The original text contained 5 footnotes which were omitted from this narration.
---
First published:
September 4th, 2025
Source:
https://www.lesswrong.com/posts/Qdgo2jYAuFRMeMRJT/natural-latents-latent-variables-stable-across-ontologies
---
Narrated by TYPE III AUDIO.
---
Images from the article:
__T3A_INLINE_LATEX_PLACEHOLDER___P[X_1, X_2, \Lambda^i] = P[\Lambda^i] \prod_j P[X_j|\Lambda^i]___T3A_INLINE_LATEX_END_PLACEHOLDER__." style="max-width: 100%;" />__T3A_INLINE_LATEX_PLACEHOLDER___\epsilon \geq D_{KL}(P[\Lambda^i, X] || P[\Lambda^i]\prod_j P[X_j|\Lambda^i])___T3A_INLINE_LATEX_END_PLACEHOLDER__." style="max-width: 100%;" />__T3A_INLINE_LATEX_PLACEHOLDER___X_1, ..., X_n___T3A_INLINE_LATEX_END_PLACEHOLDER__ if and only if __T3A_INLINE_LATEX_PLACEHOLDER___P[X, \Lambda']___T3A_INLINE_LATEX_END_PLACEHOLDER__ satisfies the graph for all __T3A_INLINE_LATEX_PLACEHOLDER___j___T3A_INLINE_LATEX_END_PLACEHOLDER__. Intuitively, it says that any one component of __T3A_INLINE_LATEX_PLACEHOLDER___X___T3A_INLINE_LATEX_END_PLACEHOLDER__ is enough to fully determine __T3A_INLINE_LATEX_PLACEHOLDER___\Lambda'___T3A_INLINE_LATEX_END_PLACEHOLDER__." style="max-width: 100%;" />Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.
View all episodes
By LessWrong
Audio note: this article contains 369 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in the episode description.
There's a details box here with the title "Background on where this post/paper came from". The box contents are omitted from this narration.This post is an overhaul of (and large improvement to) a paper we wrote about a year ago. The pdf version will hopefully be up on arxiv shortly, and we will link that from here once it's available. As of posting, this is probably the best first-stop mathematical intro to natural latents.
Abstract
Suppose two Bayesian agents each learn a generative model of the same environment. We will assume the two have converged on the predictive distribution (i.e. distribution over some observables in the environment), but may have different generative models containing different latent variables. Under [...]
---
Outline:
(00:52) Abstract
(01:42) Background
(04:12) The Math
(04:15) Setup & Objective
(07:05) Notation
(09:45) Foundational Concepts: Mediation, Redundancy & Naturality
(12:59) Core Theorems
(14:51) Naturality _\\implies_ Minimality Among Mediators
(15:59) Naturality _\\implies_ Maximality Among Redunds
(16:47) Isomorphism of Natural Latents
(17:14) Application To Translatability
(17:18) Motivating Question
(18:27) Guaranteed Translatability
(21:09) Natural Latents: Intuition & Examples
(21:24) When Do Natural Latents Exist? Some Intuition From The Exact Case
(23:11) Worked Quantitative Example of the Mediator Determines Redund Theorem
(26:54) Intuitive Examples of Natural Latents
(27:17) Ideal Gas
(28:22) Biased Die
(29:36) Timescale Separation In A Markov Chain
(30:24) Discussion & Conclusion
(33:56) Acknowledgements
(34:05) Appendices
(34:08) Graphical Notation and Some Rules for Graphical Proofs
(35:02) Frankenstein Rule
(37:39) Factorization Transfer
(39:15) Bookkeeping Rule
(40:03) The Dangly Bit Lemma
(41:09) Graphical Proofs
(41:18) Python Script for Computing _D_{KL}_ in Worked Example
The original text contained 5 footnotes which were omitted from this narration.
---
First published:
September 4th, 2025
Source:
https://www.lesswrong.com/posts/Qdgo2jYAuFRMeMRJT/natural-latents-latent-variables-stable-across-ontologies
---
Narrated by TYPE III AUDIO.
---
Images from the article:
__T3A_INLINE_LATEX_PLACEHOLDER___P[X_1, X_2, \Lambda^i] = P[\Lambda^i] \prod_j P[X_j|\Lambda^i]___T3A_INLINE_LATEX_END_PLACEHOLDER__." style="max-width: 100%;" />__T3A_INLINE_LATEX_PLACEHOLDER___\epsilon \geq D_{KL}(P[\Lambda^i, X] || P[\Lambda^i]\prod_j P[X_j|\Lambda^i])___T3A_INLINE_LATEX_END_PLACEHOLDER__." style="max-width: 100%;" />__T3A_INLINE_LATEX_PLACEHOLDER___X_1, ..., X_n___T3A_INLINE_LATEX_END_PLACEHOLDER__ if and only if __T3A_INLINE_LATEX_PLACEHOLDER___P[X, \Lambda']___T3A_INLINE_LATEX_END_PLACEHOLDER__ satisfies the graph for all __T3A_INLINE_LATEX_PLACEHOLDER___j___T3A_INLINE_LATEX_END_PLACEHOLDER__. Intuitively, it says that any one component of __T3A_INLINE_LATEX_PLACEHOLDER___X___T3A_INLINE_LATEX_END_PLACEHOLDER__ is enough to fully determine __T3A_INLINE_LATEX_PLACEHOLDER___\Lambda'___T3A_INLINE_LATEX_END_PLACEHOLDER__." style="max-width: 100%;" />Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.
More shows like LessWrong (30+ Karma)
View all
Making Sense with Sam Harris
26,388 Listeners
Conversations with Tyler
2,424 Listeners
The Peter Attia Drive
8,267 Listeners
Sean Carroll's Mindscape: Science, Society, Philosophy, Culture, Arts, and Ideas
4,145 Listeners
ManifoldOne
92 Listeners
Your Undivided Attention
1,565 Listeners
All-In with Chamath, Jason, Sacks & Friedberg
9,826 Listeners
Machine Learning Street Talk (MLST)
89 Listeners
Dwarkesh Podcast
488 Listeners
Hard Fork
5,475 Listeners
The Ezra Klein Show
16,083 Listeners
Moonshots with Peter Diamandis
534 Listeners
No Priors: Artificial Intelligence | Technology | Startups
133 Listeners
Latent Space: The AI Engineer Podcast
96 Listeners
BG2Pod with Brad Gerstner and Bill Gurley
509 Listeners