Answers are grounded in this paper and cite their sources.
Artifact report detailing machine-checked scalar foundations for SGD, ensuring transparent organization and replayability.
We present a machine-checked source containing 78 named real-arithmetic declarations that occur as local steps in standard analyses of stochastic gradient descent (SGD). This declaration count includes support identities, recovery variants, and direct restatements; it is not a count of novel or publication-credit theorems. The corpus covers sign and ordering facts, scalar forms of convexity and smoothness consequences, one-step distance rearrangements, elementary momentum and mini-batch algebra, assumed control-variate bounds, rate-shape inequalities, schedule monotonicity, and regularization terms. Forty-three selected declarations are exposed in the paper. The verification replay checks 109 registered items: 31 real-symbol registrations and 78 theorem declarations. The kernel introduces no domain axioms, but every declaration remains conditional on the assumptions displayed in its statement. In particular, the development does not define an SGD process, a probability space, a convex function, or an arbitrary-horizon iteration, and it does not prove end-to-end convergence of SGD or its variants. This is an artifact and corpus report, not a claim of new SGD mathematics; its contribution is transparent organization, replayability, and theorem-level traceability for a scalar foundation used in such analyses. Maturity: Short Draft. Target venue: Zenodo revision of record 21454788. Part of The Latent research program.
No takes yet. Share an insight, caveat, or question.
Tamás Nagy (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: