Alphabeta Math
AlgorithmAlgorithm: Literature-sourcedProof: Not applicablePipeline-generatedjudge pass (gpt-6-luna)
How statement and proof provenance work

The first chip identifies the source of the statement or construction; the second identifies the source of its local proof or verification.

  • Literature-sourced: the exact statement appears in a cited source; only wording and notation differ.
  • AI-adapted: a semantically identical restatement of literature-sourced material, modulo indexing, notation, and boundary cases adopted by the library.
  • AI-generated: a genuinely novel statement formulated by AI, with no source for the claim itself.

These labels describe origin, not correctness: citations and verification chips remain separate evidence.

RMSProp with an exponential second-moment estimate

Definition

Fix a dimension d≥1, an initial vector x1∈Rd, a finite or infinite sequence of finite gradient vectors gt∈Rd, positive step sizes ηt>0, a decay parameter ρ∈[0,1), and a denominator constant ϵ>0. Use one-based coordinate notation zi:=z(i−1) for every vector z∈Rd and 1≤i≤d. Set r0=0. At each integer round t≥1, update the second-moment estimate coordinatewise by

rt,i=ρrt−1,i+(1−ρ)gt,i2(1≤i≤d),

and then set

xt+1,i=xt,i−ηtgt,irt,i+ϵ(1≤i≤d).

For a finite gradient sequence of length T≥0, perform rounds 1≤t≤T and return the trajectory (x1,…,xT+1); when T=0, return (x1). For an infinite gradient sequence, perform every round t≥1, thereby defining and returning the iterate sequence (xt)t≥1. The root, addition, and division in the update are coordinatewise. The procedure makes no convergence or regret claim.

Definition references

The Euclidean inner product ⟨x,y⟩=∑k<nxkyk on Rn: vectors in Rd have the stated real coordinates, and vector updates are interpreted coordinatewise.

Squares of nonzero elements are positive: every nonzero squared gradient coordinate is positive.

Multiplication by zero: 0⋅a=0: a zero gradient coordinate has square zero.

Square roots exist: a unique a≥0 with (a)2=a; the positives are {x2:x≠0}: each nonnegative real has a unique nonnegative square root.

Ordered field

Sign rules for products and monotonicity of multiplication: the decay coefficients and their complements are nonnegative, so the moment recurrence preserves nonnegativity.

Bottou, Curtis, and Nocedal, RMSprop update

Reddi, Kale, and Kumar, adaptive-method setup

Remarks

This is the no-momentum RMSProp variant with a positive constant added outside the square root. It has no bias correction and defines only an update procedure.

Depends on

Used by

Dependency tree · two levels

30 results within two dependency steps of this one, each drawn at its shortest distance from it. An arrow runs from a result to what uses it, so the chart reads left to right and ends at this result, which carries a heavier outline. Every node is a link to that result. Click elsewhere on the chart to enlarge it.

Sources