Zachary Charles

Google (United States) — United States

Computer Science · Physical Sciences

15h-index5.2kcitations59works0.72yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Privacy-Preserving Technologies in Data(24), Stochastic Gradient Optimization Techniques(22), Adversarial Robustness in Machine Learning(8), Sparse and Compressive Sensing Techniques(7), Domain Adaptation and Few-Shot Learning(7)

Publications59 total

VaultGemma: A Differentially Private Gemma Model
arXiv (Cornell University)·2025Open Access
Learning with User-Level Differential Privacy Under Fixed Compute Budgets
2025· 1 cited
Communication-Efficient Language Model Training Scales Reliably and Robustly: Scaling Laws for DiLoCo
arXiv (Cornell University)·2025Open Access
Scaling Laws for Differentially Private Language Models
arXiv (Cornell University)·2025Open Access
Streaming DiLoCo with overlapping communication: Towards a Distributed Free Lunch
arXiv (Cornell University)·2025Open Access
Fine-Tuning Large Language Models with User-Level Differential Privacy
arXiv (Cornell University)·2024· 4 citedOpen Access
DrJAX: Scalable and Differentiable MapReduce Primitives in JAX
arXiv (Cornell University)·2024Open Access
Leveraging Function Space Aggregation for Federated Learning at Scale
arXiv (Cornell University)·2023Open Access
Towards Federated Foundation Models: Scalable Dataset Pipelines for Group-Structured Learning
arXiv (Cornell University)·2023· 3 citedOpen Access
Gradient Descent with Linearly Correlated Noise: Theory and Applications to Differential Privacy
arXiv (Cornell University)·2023Open Access
Federated Automatic Differentiation
arXiv (Cornell University)·2023Open Access
Federated Select: A Primitive for Communication- and Memory-Efficient Federated Learning
arXiv (Cornell University)·2022· 3 citedOpen Access
Motley: Benchmarking Heterogeneity and Personalization in Federated Learning
arXiv (Cornell University)·2022· 13 citedOpen Access
Does Federated Dropout actually work?
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)·2022· 21 cited
Optimizing the Communication-Accuracy Trade-off in Federated Learning with Rate-Distortion Theory
arXiv (Cornell University)·2022Open Access
Iterated Vector Fields and Conservatism, with Applications to Federated Learning
arXiv (Cornell University)·2021Open Access
Iterated Vector Fields and Conservatism, with Applications to Federated\n Learning
arXiv (Cornell University)·2021Open Access
A Field Guide to Federated Optimization
arXiv (Cornell University)·2021· 167 citedOpen Access
On Large-Cohort Training for Federated Learning
arXiv (Cornell University)·2021· 3 citedOpen Access
Local Adaptivity in Federated Learning: Convergence and Consistency
arXiv (Cornell University)·2021· 21 citedOpen Access
page 1 of 3Next →

Frequent Co-authors

Dimitris Papailiopoulos(16), Zachary Garrett(8), Jakub Konečný(7), Keith Rush(7), Ryan M. McKenna(5), Hongyi Wang(4), Shashank Rajput(4), Miriam Farber(4), Charles R. Johnson(4), Lee Kennedy‐Shaffer(4), Nicole Mitchell(4), H. Brendan McMahan(3), Zhouyuan Huo(3), Gauri Joshi(3), Virginia Smith(3), Hongyi Wang(3), Scott Sievert(3), Stephen J. Wright(3), Krishna Pillutla(3), Peter Kairouz(2)