paper-with-me

Papers

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

2025-08-13 · Kennon Stewart 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 $\mathcal{O}(\ln{T})$, 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.

📄 PDF Abstract BibTeX arXiv:2508.10193

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Form and Function: Machine Unlearning as a Problem of Misaligned States

2026-05-17 · Kennon Stewart arxiv

We formulate machine unlearning for online L-BFGS as a counterfactual state-alignment problem. Given an actual event stream and a deletion-edited counterfactual stream, the target of unlearning is the optimizer state tha…

Algorithms that Approximate Data Removal: New Results and Limitations

2022-09-25 · Vinith M. Suriyakumar, Ashia C. Wilson

We study the problem of deleting user data from machine learning models trained using empirical risk minimization. Our focus is on learning algorithms which return the empirical risk minimizer and approximate unlearning …

Machine Unlearning for Streaming Forgetting

2025-07-21 · Shaofei Shen, Chenhao Zhang, Yawen Zhao, Alina Bialkowski 외 arxiv

Machine unlearning aims to remove knowledge of the specific training data in a well-trained model. Currently, machine unlearning methods typically handle all forgetting data in a single batch, removing the corresponding …

Unlearning-based sliding window for continual learning under concept drift

2026-03-15 · Michal Wozniak, Marek Klonowski, Maciej Maczynski, Bartosz Krawczyk arxiv

Traditional machine learning assumes a stationary data distribution, yet many real-world applications operate on nonstationary streams in which the underlying concept evolves over time. This problem can also be viewed as…

Continual Learning

Open Problems in Machine Unlearning for AI Safety

2025-01-09 · Fazl Barez, Tingchen Fu, Ameya Prabhu, Stephen Casper 외

As AI systems become more capable, widely deployed, and increasingly autonomous in critical areas such as cybersecurity, biological research, and healthcare, ensuring their safety and alignment with human values is param…

Machine Unlearning