GaussianAccountant

class opacus.accountants.gdp.GaussianAccountant[source]
get_epsilon(delta, poisson=True)[source]

Return privacy budget (epsilon) expended so far.

Parameters
  • delta (float) – target delta

  • poisson (bool) – True is input batches was sampled via Poisson sampling, False otherwise

Return type

float

classmethod mechanism()[source]

Accounting mechanism name

Return type

str

step(*, noise_multiplier, sample_rate)[source]

Signal one optimization step

Parameters
  • noise_multiplier (float) – Current noise multiplier

  • sample_rate (float) – Current sample rate