John Rush

NeurIPS Conference 2025 Conference Paper

Communication-Efficient Language Model Training Scales Reliably and Robustly: Scaling Laws for DiLoCo

• Zachary Charles
• Gabriel Teston
• Lucio Dery
• John Rush
• Nova Fallen
• Zachary Garrett
• Arthur Szlam
• Arthur Douillard

As we scale to more massive machine learning models, the frequent synchronization demands inherent in data-parallel approaches create significant slowdowns, posing a critical challenge to further scaling. Recent work develops an approach (DiLoCo) that relaxes synchronization demands without compromising model quality. However, these works do not carefully analyze how DiLoCo's behavior changes with model size. In this work, we study the scaling law behavior of DiLoCo when training LLMs under a fixed compute budget. We focus on how algorithmic factors, including number of model replicas, hyperparameters, and token budget affect training in ways that can be accurately predicted via scaling laws. We find that DiLoCo scales both predictably and robustly with model size. When well-tuned, DiLoCo scales better than data-parallel training with model size, and can outperform data-parallel training even at small model sizes. Our results showcase a more general set of benefits of DiLoCo than previously documented, including increased optimal batch sizes, improved downstream generalization with scale, and improved evaluation loss for a fixed token budget.

NeurIPS Conference 2023 Conference Paper

(Amplified) Banded Matrix Factorization: A unified approach to private training

• Christopher A. Choquette-Choo
• Arun Ganesh
• Ryan McKenna
• H. Brendan McMahan
• John Rush
• Abhradeep Guha Thakurta
• Zheng Xu

Matrix factorization (MF) mechanisms for differential privacy (DP) have substantially improved the state-of-the-art in privacy-utility-computation tradeoffs for ML applications in a variety of scenarios, but in both the centralized and federated settings there remain instances where either MF cannot be easily applied, or other algorithms provide better tradeoffs (typically, as $\epsilon$ becomes small). In this work, we show how MF can subsume prior state-of-the-art algorithms in both federated and centralized training settings, across all privacy budgets. The key technique throughout is the construction of MF mechanisms with banded matrices (lower-triangular matrices with at most $\hat{b}$ nonzero bands including the main diagonal). For cross-device federated learning (FL), this enables multiple-participations with a relaxed device participation schema compatible with practical FL infrastructure (as demonstrated by a production deployment). In the centralized setting, we prove that banded matrices enjoy the same privacy amplification results as the ubiquitous DP-SGD algorithm, but can provide strictly better performance in most scenarios---this lets us always at least match DP-SGD, and often outperform it

NeurIPS Conference 2023 Conference Paper

Gradient Descent with Linearly Correlated Noise: Theory and Applications to Differential Privacy

• Anastasiia Koloskova
• Ryan McKenna
• Zachary Charles
• John Rush
• H. Brendan McMahan

We study gradient descent under linearly correlated noise. Our work is motivated by recent practical methods for optimization with differential privacy (DP), such as DP-FTRL, which achieve strong performance in settings where privacy amplification techniques are infeasible (such as in federated learning). These methods inject privacy noise through a matrix factorization mechanism, making the noise linearly correlated over iterations. We propose a simplified setting that distills key facets of these methods and isolates the impact of linearly correlated noise. We analyze the behavior of gradient descent in this setting, for both convex and non-convex functions. Our analysis is demonstrably tighter than prior work and recovers multiple important special cases exactly (including anticorrelated perturbed gradient descent). We use our results to develop new, effective matrix factorizations for differentially private optimization, and highlight the benefits of these factorizations theoretically and empirically.

NeurIPS Conference 2022 Conference Paper

Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streams

• Sergey Denisov
• H. Brendan McMahan
• John Rush
• Adam Smith
• Abhradeep Guha Thakurta

Motivated by recent applications requiring differential privacy in the setting of adaptive streams, we investigate the question of optimal instantiations of the matrix mechanism in this setting. We prove fundamental theoretical results on the applicability of matrix factorizations to the adaptive streaming setting, and provide a new parameter-free fixed-point algorithm for computing optimal factorizations. We instantiate this framework with respect to concrete matrices which arise naturally in the machine learning setting, and train user-level differentially private models with the resulting optimal mechanisms, yielding significant improvements on a notable problem in federated learning with user-level differential privacy.

NeurIPS Conference 2021 Conference Paper

Differentially Private Model Personalization

• Prateek Jain
• John Rush
• Adam Smith
• Shuang Song
• Abhradeep Guha Thakurta

We study personalization of supervised learning with user-level differential privacy. Consider a setting with many users, each of whom has a training data set drawn from their own distribution $P_i$. Assuming some shared structure among the problems $P_i$, can users collectively learn the shared structure---and solve their tasks better than they could individually---while preserving the privacy of their data? We formulate this question using joint, user-level differential privacy---that is, we control what is leaked about each user's entire data set. We provide algorithms that exploit popular non-private approaches in this domain like the Almost-No-Inner-Loop (ANIL) method, and give strong user-level privacy guarantees for our general approach. When the problems $P_i$ are linear regression problems with each user's regression vector lying in a common, unknown low-dimensional subspace, we show that our efficient algorithms satisfy nearly optimal estimation error guarantees. We also establish a general, information-theoretic upper bound via an exponential mechanism-based algorithm.

NeurIPS Conference 2021 Conference Paper

Federated Reconstruction: Partially Local Federated Learning

• Karan Singhal
• Hakim Sidahmed
• Zachary Garrett
• Shanshan Wu
• John Rush
• Sushant Prakash

Personalization methods in federated learning aim to balance the benefits of federated and local training for data availability, communication cost, and robustness to client heterogeneity. Approaches that require clients to communicate all model parameters can be undesirable due to privacy and communication constraints. Other approaches require always-available or stateful clients, impractical in large-scale cross-device settings. We introduce Federated Reconstruction, the first model-agnostic framework for partially local federated learning suitable for training and inference at scale. We motivate the framework via a connection to model-agnostic meta learning, empirically demonstrate its performance over existing approaches for collaborative filtering and next word prediction, and release an open-source library for evaluating approaches in this setting. We also describe the successful deployment of this approach at scale for federated collaborative filtering in a mobile keyboard application.

SODA Conference 2000 Conference Paper

A dynamic programming approach to de novo peptide sequencing via tandem mass spectrometry

• Ting Chen
• Ming-Yang Kao
• Matthew Tepel
• John Rush
• George M. Church