FA-98944 / Optimizer update state / Member archive
SGD adds the gradient instead of taking a descent step · case 04
SGD adds the gradient instead of taking a descent step.
Case contract
One scalar SGD step returns p-lr*g for finite inputs and nonnegative lr.
Why this case matters
Optimizer implementations must associate each parameter with its own mathematically specified update state.
One recorded failure
Sample boundary fixtureThis sample comes from the broken implementation of a controlled reproducer.
| Boundary fixture | Actual | Expected | Outcome |
|---|---|---|---|
| positive gradient | 13 | -3 | Failed |
MEMBER ARCHIVE
The complete case is available to members.
This record includes three runnable implementations, regression fixtures, execution results, and source hashes.
Member access is invitation-based. Sign in with your invited account to inspect the sources.
Sign in to the archive ↗