Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2605.05871 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915987451805696 |
|---|---|
| author | Cai, Junhao Kim, Dohun Kim, Dowon Choi, Sung Il Jin, Chengjun Park, Juhyun Joo, Changhee |
| author_facet | Cai, Junhao Kim, Dohun Kim, Dowon Choi, Sung Il Jin, Chengjun Park, Juhyun Joo, Changhee |
| contents | Machine unlearning seeks to remove the influence of designated training data while preserving performance on the remaining data. Approximate unlearning can be viewed as a local editing problem; in min-max unlearning, the key local object is the surrogate point at which the retain objective is evaluated. When forget and retain gradients are strongly aligned, an unconstrained forget-maximizing perturbation can move to a surrogate point that increases retain loss. We propose Retain-Orthogonal Surrogate Unlearning (ROSU), which constrains the inner surrogate construction by maximizing first-order forget gain subject to zero first-order retain change under a fixed perturbation budget. This yields a closed-form retain-orthogonal perturbation, a lightweight transported outer update, and amplification along the retain-neutral direction. Our analysis establishes (i) a curvature-controlled second-order bound on retain damage, (ii) a positive-alignment regime in which ROSU strictly reduces surrogate retain loss relative to standard min-max perturbations, and (iii) near-equivalence when the two gradients are nearly orthogonal. Across vision and language benchmarks (CIFAR-10/100, Tiny-ImageNet, TOFU, WMDP), the empirical pattern follows this geometry: ROSU gives its clearest gains in high-coupling regimes while remaining competitive elsewhere. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_05871 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Retain-Neutral Surrogates for Min-Max Unlearning Cai, Junhao Kim, Dohun Kim, Dowon Choi, Sung Il Jin, Chengjun Park, Juhyun Joo, Changhee Machine Learning Machine unlearning seeks to remove the influence of designated training data while preserving performance on the remaining data. Approximate unlearning can be viewed as a local editing problem; in min-max unlearning, the key local object is the surrogate point at which the retain objective is evaluated. When forget and retain gradients are strongly aligned, an unconstrained forget-maximizing perturbation can move to a surrogate point that increases retain loss. We propose Retain-Orthogonal Surrogate Unlearning (ROSU), which constrains the inner surrogate construction by maximizing first-order forget gain subject to zero first-order retain change under a fixed perturbation budget. This yields a closed-form retain-orthogonal perturbation, a lightweight transported outer update, and amplification along the retain-neutral direction. Our analysis establishes (i) a curvature-controlled second-order bound on retain damage, (ii) a positive-alignment regime in which ROSU strictly reduces surrogate retain loss relative to standard min-max perturbations, and (iii) near-equivalence when the two gradients are nearly orthogonal. Across vision and language benchmarks (CIFAR-10/100, Tiny-ImageNet, TOFU, WMDP), the empirical pattern follows this geometry: ROSU gives its clearest gains in high-coupling regimes while remaining competitive elsewhere. |
| title | Retain-Neutral Surrogates for Min-Max Unlearning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2605.05871 |