AI Foundationspredict · compress · act

concepts → Theorem

Theorem

Rate–distortion theory

also called Rate-distortion theory

timeless2 connections

how little damage lossy compression can do at a given number of bits — the channel chapter, made lossy

Where it sits

The prism has six jobs across and eight layers down. Its primary cell is measure × L0. Hatched cells cannot exist — a GPU does not learn, an institution does not infer.

What must come first — and what it unlocks

Left to right is reading order, derived from the prerequisite_of edges. Nothing here is hand-ordered: the diagram is the graph.

nothing comes first — this is a starting pointRate–distortion theoryInformation bottleneck

Unlocks: Information bottleneck

Where to read it

The chapter that introduces it, and any chapter that uses it again.

15The Bottleneckact IV · The Learning Floor

Where it comes from

bookElements of Information Theory (2nd ed.)Thomas M. Cover, Joy A. Thomas · 2006

Every connection

All 2 edges touching this node, grouped by relation family — the sections above are highlights from this list. Colours match the relation families inthe atlas.

Order · 1
must come beforeInformation bottleneckObjective
Contrast · 1
is dual toChannel capacityTheorem

This page is a projection of one node in src/data/concepts.ts. It has no prose file of its own — 521 declared edges produce all 340 of these pages. Edit an edge and both endpoints change.