| Age | Commit message (Collapse) | Author |
|
The 0.4x figure compared relaxation-iteration counts across methods that count
different things: the closest EP-family baseline uses asynchronous local updates
where one iteration moves information roughly one layer, while ours transmits
through the whole stack per round. Wall-clock against backprop on matched
hardware is the currency that survives that difference, and it measures 2.7x.
|
|
72M is now 3.400 vs 3.397, statistically indistinguishable rather than a 4 to 5 percent band, with the 11M, 18M and 36M rungs reported alongside. Adds the readout precision result and its verification, and marks the 135M rerun as in progress.
|
|
|
|
|
|
* Frame the 72M result as a BP match
* Clarify the 0.6B to 8B scaling roadmap
|
|
|
|
|
|
|
|
|
|
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
|
|
pre-registered protocol (user doctrine)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
|
|
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
|
|
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
|
|
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
|
|
noindex mode)
Template: github.com/eliahuhorwitz/Academic-project-page-template (CC BY-SA 4.0, attribution retained)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
|