# Continual Learning With Participation Privacy: An Auditable Buffering-Aggregation Recipe

arXiv: https://arxiv.org/abs/2607.07209 · HTML: https://mlsanity.com/paper/2607.07209/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 32 references that are in the map.
- First posted on arXiv 8 Jul 2026.

## Builds on (most cited first, 12 of 12)

- [Renyi Differential Privacy](https://mlsanity.com/paper/1702.07476/) (2017)
- [The Composition Theorem for Differential Privacy](https://mlsanity.com/paper/1311.0776/) (2013)
- [Practical and Private (Deep) Learning without Sampling or Shuffling](https://mlsanity.com/paper/2103.00039/) (2021)
- [Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streams](https://mlsanity.com/paper/2202.08312/) (2022)
- [The Price of Differential Privacy under Continual Observation](https://mlsanity.com/paper/2112.00828/) (2021)
- [Constant matters: Fine-grained Complexity of Differentially Private Continual Observation](https://mlsanity.com/paper/2202.11205/) (2022)
- [~Optimal Differentially Private Learning of Thresholds and Quasi-Concave Optimization](https://mlsanity.com/paper/2211.06387/) (2022)
- [Lower Bounds for Differential Privacy Under Continual Observation and Online Threshold Queries](https://mlsanity.com/paper/2403.00028/) (2024)
- [Concurrent Composition Theorems for Differential Privacy](https://mlsanity.com/paper/2207.08335/) (2022)
- [Differentially Private Stochastic Gradient Descent with Fixed-Size Minibatches: Tighter RDP Guarantees with or without Replacement](https://mlsanity.com/paper/2408.10456/) (2024)
- [Concurrent Composition for Interactive Differential Privacy with Adaptive Privacy-Loss Parameters](https://mlsanity.com/paper/2309.05901/) (2023)
- [Concurrent Composition for Differentially Private Continual Mechanisms](https://mlsanity.com/paper/2411.03299/) (2024)

## Abstract (arXiv)

Modern federated and streaming learning systems often release intermediate models, so privacy must hold for the full trajectory under adaptive interaction. Motivated by participation privacy, we study single-edit neighboring user streams, where one insertion/deletion shifts all subsequent updates and defeats standard Hamming-neighbor continual-release analyses. We give an auditable modular recipe. A randomized buffering wrapper emits bins of size [U,2U], reducing single-edit streams to a Hamming-style per-bin update stream with explicit backlog/delay guarantees, where U is calibrated by the privacy parameters (varepsilon,δ). We then prove a certification theorem identifying when a non-adaptive Hamming-neighbor DP proof for a continual primitive lifts to adaptive inputs: the primitive must use fresh per-round randomness and have a stable one-round privacy profile under common adaptive context. Together, these ingredients yield trajectory-level (varepsilon,δ)-DP for single-edit streams using standard primitives (e.g., tree prefix sums), with an explicit privacy--latency link via U.