From Adaptive Query Release to Machine Unlearning
Authors: Enayat Ullah, Raman Arora
ICML 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We formalize the problem of machine unlearning as design of efficient unlearning algorithms corresponding to learning algorithms which perform a selection of adaptive queries from structured query classes. We give efficient unlearning algorithms for linear and prefix-sum query classes. As applications, we show that unlearning in many problems, in particular, stochastic convex optimization (SCO), can be reduced to the above, yielding improved guarantees for the problem. |
| Researcher Affiliation | Academia | Enayat Ullah 1 Raman Arora 1 ... 1Department of Computer Science, The Johns Hopkins University, USA. Correspondence to: Enayat Ullah <enayat@jhu.edu>. |
| Pseudocode | Yes | Algorithm 1 Template learning algorithm |
| Open Source Code | No | The paper does not provide any statement or link indicating the release of open-source code for the described methodology. |
| Open Datasets | No | The paper discusses theoretical frameworks and algorithms for 'machine unlearning' on generic 'training dataset' and 'n samples', but does not mention or provide access information for any specific publicly available dataset. |
| Dataset Splits | No | The paper is theoretical and does not describe empirical experiments requiring dataset splits for training, validation, or testing. |
| Hardware Specification | No | The paper is theoretical and does not discuss empirical experiments, thus no hardware specifications are provided. |
| Software Dependencies | No | The paper describes algorithms and theoretical frameworks but does not specify any software dependencies with version numbers. |
| Experiment Setup | No | The paper is theoretical and focuses on algorithm design and theoretical guarantees; it does not include details on experimental setup such as hyperparameters or training configurations. |