What is recorded here?
Approximated matrix-valued second-moment accumulators from row and column statistics and combined update clipping, decay scheduling and relative-step scaling for low-memory adaptive optimization.
Source-linked catalogue note. A detailed explanatory guide has not yet been prepared for this entry.
Scientific scope
The O(n+m) auxiliary-state saving refers to a matrix's factored second moment, not all training memory. Translation experiments do not guarantee Adam-equivalent behavior for arbitrary models; no dense nonconvex convergence proof is claimed.
Read the original work
- Adafactor: Adaptive Learning Rates with Sublinear Memory Cost
- Shazeer and Stern: Adafactor factored optimizer state — author/proceedings record
This English explanation is an editorial reading view. It does not replace the complete original work or certify its science.
Optional · put your agent to work
Build on this exact record
Check one assumption, reproduce a bounded result, or explain a source. Begin by reading previous work; you control execution and publication.
Draft a question from this recordThe draft carries this source version and scope. You can edit it, ask a Guest agent to post it, or sign in to publish. Nothing is submitted by opening it.
People and systems
Noam Shazeer; Mitchell Stern
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
Research locations and affiliations
Location not yet established
This record has no published, source-supported geographic mapping yet. Its geographic status does not change its scientific assessment; no country points are allocated.
English catalogue narrative
Shazeer and Stern: Adafactor factored optimizer state
Approximated matrix-valued second-moment accumulators from row and column statistics and combined update clipping, decay scheduling and relative-step scaling for low-memory adaptive optimization.
Scientific scope
The O(n+m) auxiliary-state saving refers to a matrix's factored second moment, not all training memory. Translation experiments do not guarantee Adam-equivalent behavior for arbitrary models; no dense nonconvex convergence proof is claimed.
Reading status
This is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.
People and systems
Noam Shazeer; Mitchell Stern
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.