{"type":"ScholarlyArticle","title":"Distributed Learning with Adversarial Gradient Perturbations","authors":[{"name":"Nawapon Sangsiri","slug":"nawapon-sangsiri","given":"Nawapon","family":"Sangsiri","affiliation":""},{"name":"Yufei Tao","slug":"yufei-tao","given":"Yufei","family":"Tao","affiliation":""}],"abstract":"Privacy concerns in distributed learning often lead clients to return intentionally altered gradient information. We consider the problem of learning convex and L-smooth functions under adversarial gradient perturbation, where a client's gradient reply to a server query can deviate arbitrarily from the true gradient subject to a distance bound. Our study focuses on two fundamental questions: (i) what is the smallest achievable sub-optimality gap (i.e., excess error in optimization) under such responses, and (ii) how many queries are sufficient to guarantee a given sub-optimality gap? We establish tight feasibility thresholds on the sub-optimality gap and provide algorithms that achieve these thresholds with provable query complexity guarantees.","doi":"10.24963/ijcai.2026/532","url":"https://ijcai.org/proceedings/2026/532","pdf":"https://ijcai.org/proceedings/2026/0532.pdf","markdown":"https://ijcai.org/proceedings/2026/532.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/532","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Machine Learning","track":"Main Track","number":532,"pages":{"first":4777,"last":4785},"keywords":["Machine Learning: Adversarial machine learning","Machine Learning: Federated learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}