Skip to main content

🏷️ Docs

Status:ValidIn progress
Tags:Project
Last modified:

How to use this section

Use this page as the technical documentation entry point. The sidebar is organized around the artifacts that define an experiment: formulation, implementation, datasets, models, ablation tests, controllers, and experiment records.

Main Sections​

SectionPurpose
FormulationMathematical framing for fixed-point online learning and global throttling.
ImplementationCode-facing reference for the Python modules and training loop.
DatasetsStable dataset IDs used in experiment traces.
ModelsStable model IDs used in experiment traces.
Ablation TestsStress-test families used to make fixed-point training fail in controlled ways.
ControllersStable controller IDs used to modify or throttle optimizer updates.
ExperimentsActual experiment reports, plots, notebooks, and conclusions.

Experiment Trace Pattern​

Most technical pages should eventually support experiment traces of the form:

dataset: DS-...
model: MDL-...
precision: PREC-...
stress_test: ST-...
optimizer: ...
controller: CTRL-...
metrics: [...]