English
Related papers

Related papers: DP-SGD Without Clipping: The Lipschitz Neural Netw…

200 papers

Differentially private stochastic gradient descent (DP-SGD) is known to have poorer training and test performance on large neural networks, compared to ordinary stochastic gradient descent (SGD). In this paper, we perform a detailed study…

Machine Learning · Computer Science 2023-11-14 Lauren Watson , Eric Gan , Mohan Dantam , Baharan Mirzasoleiman , Rik Sarkar

This paper tackles the problem of Lipschitz regularization of Convolutional Neural Networks. Lipschitz regularity is now established as a key property of modern deep learning with implications in training stability, generalization,…

Machine Learning · Computer Science 2020-11-10 Alexandre Araujo , Benjamin Negrevergne , Yann Chevaleyre , Jamal Atif

Graph neural networks (GNNs) have gained an increasing amount of popularity due to their superior capability in learning node embeddings for various graph inference tasks, but training them can raise privacy concerns. To address this, we…

Machine Learning · Computer Science 2023-09-08 Xiaochen Zhu , Vincent Y. F. Tan , Xiaokui Xiao

Computing tight Lipschitz bounds for deep neural networks is crucial for analyzing their robustness and stability, but existing approaches either produce relatively conservative estimates or rely on semidefinite programming (SDP)…

Machine Learning · Computer Science 2025-03-19 Usman Syed , Bin Hu

This paper proposes a sensitivity analysis framework based on set valued mapping for deep neural networks (DNN) to understand and compute how the solutions (model weights) of DNN respond to perturbations in the training data. As a DNN may…

Machine Learning · Computer Science 2024-12-17 Xin Wang , Feilong Wang , Xuegang Ban

Developing machine learning methods that are privacy preserving is today a central topic of research, with huge practical impacts. Among the numerous ways to address privacy-preserving learning, we here take the perspective of computing the…

Machine Learning · Computer Science 2021-07-06 Alain Rakotomamonjy , Liva Ralaivola

Large language models (LLMs) are commonly adapted to downstream tasks through fine-tuning, but fine-tuning data often contains sensitive information that may be leaked by the resulting model. Differential privacy (DP) offers formal…

Machine Learning · Computer Science 2026-05-19 Haichao Sha , Zihao Wang , Yuncheng Wu , Hong Chen , Wei Dong

Knowledge distillation has become one of the most important model compression techniques by distilling knowledge from larger teacher networks to smaller student ones. Although great success has been achieved by prior distillation methods…

Machine Learning · Computer Science 2021-08-31 Yuzhang Shang , Bin Duan , Ziliang Zong , Liqiang Nie , Yan Yan

Differential privacy (DP) is a prominent method for protecting information about individuals during data analysis. Training neural networks with differentially private stochastic gradient descent (DPSGD) influences the model's learning…

Machine Learning · Computer Science 2025-10-10 Lea Demelius , Dominik Kowald , Simone Kopeinik , Roman Kern , Andreas Trügler

Differentially private training algorithms like DP-SGD protect sensitive training data by ensuring that trained models do not reveal private information. An alternative approach, which this paper studies, is to use a sensitive dataset to…

Machine Learning · Computer Science 2024-01-12 Alexey Kurakin , Natalia Ponomareva , Umar Syed , Liam MacDermed , Andreas Terzis

Large language models (LLMs) frequently memorize sensitive or personal information, raising significant privacy concerns. Existing variants of differential privacy stochastic gradient descent (DPSGD) inject uniform noise into every gradient…

Machine Learning · Computer Science 2025-09-30 Manjiang Yu , Priyanka Singh , Xue Li , Yang Cao

In this paper, we propose BPGrad, a novel approximate algorithm for deep nueral network training, based on adaptive estimates of feasible region via branch-and-bound. The method is based on the assumption of Lipschitz continuity in…

Computer Vision and Pattern Recognition · Computer Science 2021-10-26 Yuanwei Wu , Ziming Zhang , Guanghui Wang

In privacy-preserving machine learning, differentially private stochastic gradient descent (DP-SGD) performs worse than SGD due to per-sample gradient clipping and noise addition. A recent focus in private learning research is improving the…

Computer Vision and Pattern Recognition · Computer Science 2023-11-01 Xinyu Tang , Ashwinee Panda , Vikash Sehwag , Prateek Mittal

Lipschitz Bound Estimation is an effective method of regularizing deep neural networks to make them robust against adversarial attacks. This is useful in a variety of applications ranging from reinforcement learning to autonomous systems.…

Machine Learning · Computer Science 2022-07-18 Sarosij Bose

We study the problem of differentially private linear regression where each data point is sampled from a fixed sub-Gaussian style distribution. We propose and analyze a one-pass mini-batch stochastic gradient descent method (DP-AMBSSGD)…

Machine Learning · Computer Science 2022-07-14 Prateek Varshney , Abhradeep Thakurta , Prateek Jain

We provide a theoretical explanation for the effectiveness of gradient clipping in training deep neural networks. The key ingredient is a new smoothness condition derived from practical neural network training examples. We observe that…

Optimization and Control · Mathematics 2020-02-12 Jingzhao Zhang , Tianxing He , Suvrit Sra , Ali Jadbabaie

Despite intense interest and considerable effort, the current generation of neural networks suffers a significant loss of accuracy under most practically relevant privacy training regimes. One particularly challenging class of neural…

Machine Learning · Computer Science 2021-06-07 Huanyu Zhang , Ilya Mironov , Meisam Hejazinia

We design the first node-differentially private algorithm for approximating the number of connected components in a graph. Given a database representing an $n$-vertex graph $G$ and a privacy parameter $\varepsilon$, our algorithm runs in…

Data Structures and Algorithms · Computer Science 2023-04-17 Iden Kalemaj , Sofya Raskhodnikova , Adam Smith , Charalampos E. Tsourakakis

Gradient clipping is a standard safeguard for training neural networks under noisy, heavy-tailed stochastic gradients; yet, most clipping rules treat all parameters as vectors and ignore the matrix structure of modern architectures. We show…

Machine Learning · Computer Science 2026-05-13 Alexander Yukhimchuk , Mladen Kolar , Martin Takáč , Sayantan Choudhury

Differentially private stochastic gradient descent (DP-SGD) is the most widely used method for training machine learning models with provable privacy guarantees. A key challenge in DP-SGD is setting the per-sample gradient clipping…

Machine Learning · Computer Science 2025-10-29 Atefeh Gilani , Naima Tasnim , Lalitha Sankar , Oliver Kosut