No article text was recorded for this version.
privacy amplification by iteration
Version 1 of 129 papers74 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Differentially Private Learning Needs Hidden State (Or Much Faster Convergence)
- Blog: Privacy of Noisy Stochastic Gradient Descent: More Iterations without More Privacy Loss
- Blog: Privacy Amplification by Iteration
- Blog: Privacy Amplification in Differentially Private Zeroth-Order Optimization with Hidden States
- Blog: Privacy Amplification by Iteration for ADMM with (Strongly) Convex Objective Functions
- Blog: Privacy Amplification via Iteration for Shuffled and Online PNSGD
- Blog: Shifted Interpolation for Differential Privacy
- Blog: It's Our Loss: No Privacy Amplification for Hidden State DP-SGD With Non-Convex Loss
- Blog: Convergent Privacy Loss of Noisy-SGD without Convexity and Smoothness
- Blog: Convergent Differential Privacy Analysis for General Federated Learning
- Blog: Differentially Private Graph Diffusion with Applications in Personalized PageRanks
- Blog: Renyi Differentially Private ERM for Smooth Objectives
- Blog: Differential Privacy Dynamics of Langevin Diffusion and Noisy Gradient Descent
- Blog: An Improved Privacy and Utility Analysis of Differentially Private SGD with Bounded Domain and Smooth Losses
- Blog: Convex Approximation of Two-Layer ReLU Networks for Hidden State Differential Privacy
- Blog: Bolt-on Differential Privacy for Scalable Stochastic Gradient Descent-based Analytics
- Blog: Certified Unlearning for Neural Networks
- Blog: From Noisy Fixed-Point Iterations to Private ADMM for Centralized and Federated Learning
- Blog: Rényi Pufferfish Privacy: General Additive Noise Mechanisms and Privacy Amplification by Iteration via Shift Reduction Lemmas
- Blog: Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model
- Blog: Can Stochastic Gradient Langevin Dynamics Provide Differential Privacy for Deep Learning?
- Blog: Private Stochastic Convex Optimization: Optimal Rates in Linear Time
- Blog: Privacy Amplification by Mixing and Diffusion Mechanisms
- Blog: Better Rates for Private Linear Regression in the Proportional Regime via Aggressive Clipping
- Blog: Unified Enhancement of Privacy Bounds for Mixture Mechanisms via $f$-Differential Privacy
- Blog: Differential Privacy Guarantees of Markov Chain Monte Carlo Algorithms
- Blog: Beyond the Calibration Point: Mechanism Comparison in Differential Privacy
- Blog: Privacy of Noisy Stochastic Gradient Descent: More Iterations without More Privacy Loss
- Blog: Differentially Private Neural Network Training under Hidden State Assumption
History & citation
Current · Permanent link
- This direction split from Privacy Amplification by Iteration in Hidden State Models (55% overlap)
- This direction split from non-convex optimization gap (convexity constraint) (59% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_privacy_amplification_by_iteration_69836bfb,
title = {privacy amplification by iteration},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/privacy-amplification-by-iteration/rdr_69836bfb8bed49ddbecf99c46768546a},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 1, frozen text):
@misc{lacuna_privacy_amplification_by_iteration_69836bfb_v1,
title = {privacy amplification by iteration},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/privacy-amplification-by-iteration/rdr_69836bfb8bed49ddbecf99c46768546a/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-22},
}