paper-with-me

홈 › Papers

Scaling Laws for Differentially Private Language Models

2025-01-31 · Ryan McKenna, Yangsibo Huang, Amer Sinha, Borja Balle, Zachary Charles, Christopher A. Choquette-Choo, Badih Ghazi, George Kaissis, Ravi Kumar, Ruibo Liu, Da Yu, Chiyuan Zhang

Scaling laws have emerged as important components of large language model (LLM) training as they can predict performance gains through scale, and provide guidance on important hyper-parameter choices that would otherwise be expensive. LLMs also rely on large, high-quality training datasets, like those sourced from (sometimes sensitive) user data. Training models on this sensitive user data requires careful privacy protections like differential privacy (DP). However, the dynamics of DP training are significantly different, and consequently their scaling laws are not yet fully understood. In this work, we establish scaling laws that accurately model the intricacies of DP LLM training, providing a complete picture of the compute-privacy-utility tradeoffs and the optimal training configurations in many settings.

📄 PDF Abstract BibTeX arXiv:2501.18914

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingLarge Language Model

Similar Papers 제목 키워드 기반

A Closer Look at the Calibration of Differentially Private Learners

2022-10-15 · HANLIN ZHANG, Xuechen Li, Prithviraj Sen, Salim Roukos 외

We systematically study the calibration of classifiers trained with differentially private stochastic gradient descent (DP-SGD) and observe miscalibration across a wide range of vision and language tasks. Our analysis id…

TAN Without a Burn: Scaling Laws of DP-SGD

2022-10-07 · Tom Sander, Pierre Stock, Alexandre Sablayrolles

Differentially Private methods for training Deep Neural Networks (DNNs) have progressed recently, in particular with the use of massive batches and aggregated data augmentations for a large number of training steps. Thes…

Image Classification with Differential Privacy

Debugging Differential Privacy: A Case Study for Privacy Auditing

2022-02-24 · Florian Tramer, Andreas Terzis, Thomas Steinke, Shuang Song 외

Differential Privacy can provide provable privacy guarantees for training data in machine learning. However, the presence of proofs does not preclude the presence of errors. Inspired by recent advances in auditing which …

Reproducible scaling laws for contrastive language-image learning

2022-12-14 · CVPR 2023 1 · Mehdi Cherti, Romain Beaumont, Ross Wightman, Mitchell Wortsman 외

Scaling up neural networks has led to remarkable performance across a wide range of tasks. Moreover, performance often follows reliable scaling laws as a function of training set size, model size, and compute, which offe…

Image ClassificationOpen Vocabulary Attribute DetectionRetrievalzero-shot-classification+3

Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping

2022-12-03 · Jiyan He, Xuechen Li, Da Yu, Huishuai Zhang 외

Differentially private deep learning has recently witnessed advances in computational efficiency and privacy-utility trade-off. We explore whether further improvements along the two axes are possible and provide affirmat…

Computational Efficiency