Generalizing DP-SGD with Shuffling and Batch Clipping
Classical differential private DP-SGD implements individual clipping with random subsampling, which forces a mini-batch SGD approach. We provide a general differential private algorithmic framework that goes beyond DP-SGD and allows any possible first order optimizers (e.g., classical SGD and momentum based SGD approaches) in combination with batch clipping, which clips an aggregate of computed gradients rather than summing clipped gradients (as is done in individual clipping). The framework also admits sampling techniques beyond random subsampling such as shuffling. Our DP analysis follows the $f$-DP approach and introduces a new proof technique which allows us to derive simple closed form expressions and to also analyse group privacy. In particular, for $E$ epochs work and groups of size $g$, we show a $\sqrt{g E}$ DP dependency for batch clipping with shuffling.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Differentially Private Block-wise Gradient Shuffle for Deep Learning
Traditional Differentially Private Stochastic Gradient Descent (DP-SGD) introduces statistical noise on top of gradients drawn from a Gaussian distribution to ensure privacy. This paper introduces the novel Differentiall…
Deep LearningRevisit Micro-batch Clipping: Adaptive Data Pruning via Gradient Manipulation
Micro-batch clipping, a gradient clipping method, has recently shown potential in enhancing auto-speech recognition (ASR) model performance. However, the underlying mechanism behind this improvement remains mysterious, p…
speech-recognitionSpeech RecognitionMinibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond
In distributed learning, local SGD (also known as federated averaging) and its simple baseline minibatch SGD are widely studied optimization methods. Most existing analyses of these methods assume independent and unbiase…
To Shuffle or not to Shuffle: Auditing DP-SGD with Shuffling
The Differentially Private Stochastic Gradient Descent (DP-SGD) algorithm allows the training of machine learning (ML) models with formal Differential Privacy (DP) guarantees. Since DP-SGD processes training data in batc…
Error dynamics of mini-batch gradient descent with random reshuffling for least squares regression
We study the discrete dynamics of mini-batch gradient descent with random reshuffling for least squares regression. We show that the training and generalization errors depend on a sample cross-covariance matrix $Z$ betwe…
regression