{"ID":2875500,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.02433","arxiv_id":"2509.02433","title":"VASSO: Variance Suppression for Sharpness-Aware Minimization","abstract":"Sharpness-aware minimization (SAM) has well-documented merits in enhancing generalization of deep neural network models. Accounting for sharpness in the loss function geometry, where neighborhoods of `flat minima' heighten generalization ability, SAM seeks `flat valleys' by minimizing the maximum loss provoked by an adversarial perturbation within the neighborhood. Although critical to account for sharpness of the loss function, in practice SAM suffers from `over-friendly adversaries,' which can curtail the outmost level of generalization. To avoid such `friendliness,' the present contribution fosters stabilization of adversaries through variance suppression (VASSO). VASSO offers a general approach to provably stabilize adversaries. In particular, when integrating VASSO with SAM, improved generalizability is numerically validated on extensive vision and language tasks. Once applied on top of a computationally efficient SAM variant, VASSO offers a desirable generalization-computation tradeoff.","short_abstract":"Sharpness-aware minimization (SAM) has well-documented merits in enhancing generalization of deep neural network models. Accounting for sharpness in the loss function geometry, where neighborhoods of `flat minima' heighten generalization ability, SAM seeks `flat valleys' by minimizing the maximum loss provoked by an ad...","url_abs":"https://arxiv.org/abs/2509.02433","url_pdf":"https://arxiv.org/pdf/2509.02433v1","authors":"[\"Bingcong Li\",\"Yilang Zhang\",\"Georgios B. Giannakis\"]","published":"2025-09-02T15:35:46Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false}