Unverified50% confidenceFactExact time
Under a linear-quadratic simplification, the paper derives a square-root allocation law: the noise variance (or the allocation of privacy budget) is inversely proportional to the square root of the number of iterations.
1
Sources
50%
Confidence
Long-term
Relevance
10/30/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedDifferential privacy noise reduces data utility, federated learning has communication overhead and model convergence challenges, and synthetic data may introduce distributional bias.64% similarUnverifiedIn differential privacy, the smaller the privacy budget ε, the stronger the privacy protection, but the larger the noise introduced, causing the estimation error to rise.62% similarUnverifiedThe paper proposes the Privacy-Budget Adjoint Mirror Descent (PB-AMD) algorithm, which combines pathwise adjoint gradients with entropy updates to solve for the noise variance schedule.61% similarUnverifiedThe paper lists how to quantify the distribution gap between synthetic environments and real systems as one of the open problems.61% similarUnverifiedUnder the square-root learning rate scaling rule, the noise magnitude shrinks as 1/√k as the batch increases, so scaling the learning rate by √k exactly maintains the gradient's signal-to-noise ratio unchanged.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1114512API
curl https://kongchang.com/api/v1/knowledge/claims/1114512MCP
get_claim(id=1114512)