Margin Notes

A notebook on statistical learning

Ideas, in the
margins.

Papers on statistical learning, read through their questions, methods, and limits. Follow the ideas; keep the original sources close.

Statistics · Learning · Reproducible evidencePaper notes, with sources in view

The notebook

08 NOTES
01
Learning methodsPaper note

Reusing a Transformer block

Shared parameters, repeated computation, and task-dependent benefits.

02
Learning methodsPaper note

Depth as a fixed point

An equilibrium representation separates model definition from its numerical solver.

03
Learning methodsPaper note

When shared parameters improve estimation

A reading of the public abstract: parameters, iteration, and accuracy.

04
UncertaintyPaper note

What a coverage guarantee means

Calibration turns a score into a prediction set with a stated guarantee.

05
UncertaintyPaper note

What generated scores tell us about uncertainty

Reading GSI through its coverage guarantee and generator requirements.

06
Research practiceReading guide

How to read a statistical guarantee

A practical way to connect a theorem’s assumptions, probability statement, and conclusion to the question you actually want to answer.

07
Research practiceReading guide

What makes a comparison fair?

A good benchmark starts with a clear question, an appropriate evaluation design, and an explicit account of the resources each method uses.

08
Research practiceReading guide

From a result to reproducible evidence

Build a clear path from the research claim to its inputs, analysis, and outputs, so another person can inspect and repeat the work.

8 of 8 notesRead with curiosity. Keep the conditions.

A way of reading

Less noise.
More understanding.

01

Start with the question

Name the problem before reaching for a method.

02

Stay close to the evidence

Keep assumptions and conclusions in the same frame.

03

Leave the limits visible

A useful result also tells us where it stops.