paper-with-me

홈 › Papers

DP-SGD Without Clipping: The Lipschitz Neural Network Way

2023-05-25 · Louis Bethune, Thomas Massena, Thibaut Boissin, Yannick Prudent, Corentin Friedrich, Franck Mamalet, Aurelien Bellet, Mathieu Serrurier, David Vigouroux

State-of-the-art approaches for training Differentially Private (DP) Deep Neural Networks (DNN) face difficulties to estimate tight bounds on the sensitivity of the network's layers, and instead rely on a process of per-sample gradient clipping. This clipping process not only biases the direction of gradients but also proves costly both in memory consumption and in computation. To provide sensitivity bounds and bypass the drawbacks of the clipping process, we propose to rely on Lipschitz constrained networks. Our theoretical analysis reveals an unexplored link between the Lipschitz constant with respect to their input and the one with respect to their parameters. By bounding the Lipschitz constant of each layer with respect to its parameters, we prove that we can train these networks with privacy guarantees. Our analysis not only allows the computation of the aforementioned sensitivities at scale, but also provides guidance on how to maximize the gradient-to-noise ratio for fixed privacy guarantees. The code has been released as a Python package available at https://github.com/Algue-Rythme/lip-dp

📄 PDF Abstract BibTeX arXiv:2305.16202

Code (1)

algue-rythme/lip-dp 공식 구현 tf

Tasks

Sensitivity

Similar Papers 제목 키워드 기반

On the Convergence of Differentially Private Federated Learning on Non-Lipschitz Objectives, and with Normalized Client Updates

2021-06-13 · Rudrajit Das, Abolfazl Hashemi, Sujay Sanghavi, Inderjit S. Dhillon

There is a dearth of convergence results for differentially private federated learning (FL) with non-Lipschitz objective functions (i.e., when gradient norms are not bounded). The primary reason for this is that the clip…

BenchmarkingFederated LearningQuantizationSensitivity

Stability and Convergence of Stochastic Gradient Clipping: Beyond Lipschitz Continuity and Smoothness

2021-02-12 · Vien V. Mai, Mikael Johansson

Stochastic gradient algorithms are often unstable when applied to functions that do not have Lipschitz-continuous and/or bounded gradients. Gradient clipping is a simple and effective technique to stabilize the training …

Optimal lower Lipschitz bounds for ReLU layers, saturation, and phase retrieval

2025-02-14 · Daniel Freeman, Daniel Haider

The injectivity of ReLU layers in neural networks, the recovery of vectors from clipped or saturated measurements, and (real) phase retrieval in $\mathbb{R}^n$ allow for a similar problem formulation and characterization…

Retrieval

Lipschitz Constrained GANs via Boundedness and Continuity

2018-03-16 · Kanglin Liu, Guoping Qiu

One of the challenges in the study of Generative Adversarial Networks (GANs) is the difficulty of its performance control. Lipschitz constraint is essential in guaranteeing training stability for GANs. Although heuristic…

On the regularization of Wasserstein GANs

2017-09-26 · ICLR 2018 1 · Henning Petzka, Asja Fischer, Denis Lukovnicov

Since their invention, generative adversarial networks (GANs) have become a popular approach for learning to model a distribution of real (unlabeled) data. Convergence problems during training are overcome by Wasserstein…