# Mo' Memory, Mo' Problems: Stream-Native Machine Unlearning

arXiv: https://arxiv.org/abs/2508.10193 · HTML: https://mlsanity.com/paper/2508.10193/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 11 of its 16 references that are in the map.
- First posted on arXiv 13 Aug 2025.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 11 of 11)

- [Certified Data Removal from Machine Learning Models](https://mlsanity.com/paper/1911.03030/) (2019)
- [Making AI Forget You: Data Deletion in Machine Learning](https://mlsanity.com/paper/1907.05012/) (2019)
- [Remember What You Want to Forget: Algorithms for Machine Unlearning](https://mlsanity.com/paper/2103.03279/) (2021)
- [Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds](https://mlsanity.com/paper/1605.02065/) (2016)
- [Descent-to-Delete: Gradient-Based Methods for Machine Unlearning](https://mlsanity.com/paper/2007.02923/) (2020)
- [Adaptive Machine Unlearning](https://mlsanity.com/paper/2106.04378/) (2021)
- [A Stochastic Quasi-Newton Method for Large-Scale Optimization](https://mlsanity.com/paper/1401.7020/) (2014)
- [A Linearly-Convergent Stochastic L-BFGS Algorithm](https://mlsanity.com/paper/1508.02087/) (2015)
- [Global Convergence of Online Limited Memory BFGS](https://mlsanity.com/paper/1409.2045/) (2014)
- [Hessian-Free Online Certified Unlearning](https://mlsanity.com/paper/2404.01712/) (2024)
- [When to Forget? Complexity Trade-offs in Machine Unlearning](https://mlsanity.com/paper/2502.17323/) (2025)

## Abstract (arXiv)

Machine unlearning work assumes a static, i.i.d training environment that doesn't truly exist. Modern ML pipelines need to learn, unlearn, and predict continuously on production streams of data. We translate batch unlearning to the online setting using notions of regret, sample complexity, and deletion capacity. We tighten regret bounds to a logarithmic O(lnT), a first for a certified unlearning algorithm. When fitted with an online variant of L-BFGS optimization, the algorithm achieves state of the art regret with a constant memory footprint. Such changes extend the lifespan of an ML model before expensive retraining, making for a more efficient unlearning process.