accountant · noiseMultiplier returns sigma

Read the equation

This relation defines noiseMultiplier returns sigma in the source section “accountant · noiseMultiplier returns sigma”. It specifies the displayed relationship between the named quantities or parameters. Its interpretation depends on the source’s stated variables and conditions; this record does not assign an unprovided physical or cognitive meaning to them.

Terms & definitions

The recovered passage does not supply a separate symbol table. Read the source context for the notation used in this version; familiar letters may carry different meanings in other builds.

How it works

1. Read noiseMultiplier returns sigma as the quantity being defined or updated by this relation.

2. Substitute the source-defined variables or recorded values and follow the displayed arithmetic and indexing exactly.

3. Use this version’s variable definitions and update order. The same symbol may be assigned a different meaning in another build.

Assumptions & limits

• This source expression was recovered from the pinned code revision. Its presence does not establish that the associated program was built, run, or scientifically validated.

Original context

// is the closed form alpha / (2 * sigma^2). This is the standard Gaussian mechanism RDP curve (Mironov 2017,
// cited in docs/AI_RESEARCH.md, the federated learning with differential privacy section).
type GaussianRelease struct {
	NoiseSigma float64 // standard deviation of the added Gaussian noise, in the same units as the clip norm
	ClipNorm   float64 // the L2 clip norm C, the per tenant sensitivity; must be greater than zero
}

// noiseMultiplier returns sigma = NoiseSigma / ClipNorm, the noise measured in units of the sensitivity, the
// only quantity the Gaussian RDP curve depends on. A non positive clip norm or non positive noise sigma is a
// programming error and yields NaN, so the per release RDP is NaN and the accountant rejects it rather than
// silently treating an invalid mechanism as zero privacy loss.
func (r GaussianRelease) noiseMultiplier() float64 {
	if r.ClipNorm <= 0 || r.NoiseSigma <= 0 {
		return math.NaN()
	}
	return r.NoiseSigma / r.ClipNorm
}

noiseMultiplier returns sigma = NoiseSigma / ClipNorm, the noise measured in units of the sensitivity, the

Related builds