On Memorization and Privacy Risks of Sharpness Aware Minimization
In many recent works, there is an increased focus on designing algorithms that seek flatter optima for neural network loss optimization as there is empirical evidence that it leads to better generalization performance in many datasets. In this work, we dissect these performance gains through the lens of data memorization in overparameterized models. We define a new metric that helps us identify which data points specifically do algorithms seeking flatter optima do better when compared to vanilla SGD. We find that the generalization gains achieved by Sharpness Aware Minimization (SAM) are particularly pronounced for atypical data points, which necessitate memorization. This insight helps us unearth higher privacy risks associated with SAM, which we verify through exhaustive empirical evaluations. Finally, we propose mitigation strategies to achieve a more desirable accuracy vs privacy tradeoff.
Code (0)
등록된 구현이 없습니다.
Tasks
MemorizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning
Learning from Noisy Labels (LNL) remains a fundamental challenge in deep learning because real-world datasets often contain corrupted annotations. Most existing methods rely on label correction or sample selection mechan…
DP$^2$-FedSAM: Enhancing Differentially Private Federated Learning Through Personalized Sharpness-Aware Minimization
Federated learning (FL) is a distributed machine learning approach that allows multiple clients to collaboratively train a model without sharing their raw data. To prevent sensitive information from being inferred throug…
Federated LearningPersonalized Federated LearningOperationalizing Data Minimization for Privacy-Preserving LLM Prompting
The rapid deployment of large language models (LLMs) in consumer applications has led to frequent exchanges of personal information. To obtain useful responses, users often share more than necessary, increasing privacy r…
Beyond Local Sharpness: Communication-Efficient Global Sharpness-aware Minimization for Federated Learning
Federated learning (FL) enables collaborative model training with privacy preservation. Data heterogeneity across edge devices (clients) can cause models to converge to sharp minima, negatively impacting generalization a…
Federated LearningSharpness-Aware Machine Unlearning
We characterize the effectiveness of Sharpness-aware minimization (SAM) under machine unlearning scheme, where unlearning forget signals interferes with learning retain signals. While previous work prove that SAM improve…
DenoisingMachine UnlearningMemorization