From the 1 of 5 linked papers with an AI index.
5 papers
Ball Differential Privacy: How to Mitigate Data Reconstruction with Less Noise
Joseph Margaryan, Nirupam Gupta
The paper introduces Ball-DP, a variant of differential privacy that limits indistinguishability to records within a bounded radius in embedding space, allowing less noise and high…
Tight Stability Bounds for Robust Distributed Learning: Byzantine Failures Hurt Generalization More than Data Poisoning
Thomas Boudou, Batiste Le Bars, Nirupam Gupta +1
Robust distributed learning algorithms aim to maintain reliable performance despite the presence of misbehaving workers. Such misbehaviors are commonly modeled as \textit{Byzantine…
Unveiling the Non-Monotonic Effect of Privacy on Generalization under Byzantine Robustness
Thomas Boudou, Batiste Le Bars, Nirupam Gupta +1
Recent work has established a fundamental trilemma between Byzantine robustness, local differential privacy (LDP), and optimization error in distributed learning. We show that this…
Dangerous Liaisons of Convex Learning and Non-Affine Aggregation
Thomas Boudou, Batiste Le Bars, Nirupam Gupta +1
Last-iterate convergence and generalization guarantees in first-order convex learning hinge on the monotonicity of the update operator. While linear averaging preserves the monoton…
Reconciling Communication Compression and Byzantine-Robustness in Distributed Learning
Diksha Gupta, Antonio Honsell, Chuan Xu +2
Distributed learning enables scalable model training over decentralized data, but remains hindered by Byzantine faults and high communication costs. While both challenges have been…