Zachary Charles
14 papers · 2018–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
π Academic Marathon (7) π£ Hot Topic Early Bird π§ Keyword Pioneer π Conference Polyglot (6) π Cross-Pollinator (11)
π
Academic Marathon
(7)
π£
Hot Topic Early Bird
π
Cross-Pollinator
(11)
ποΈ
Keyword Collector
(58)
π
Century Club
(14)
π₯
Unstoppable
(5)
β
The Questioner
Conferences
NIPS (5)
ICML (4)
AISTATS (2)
ALT (1)
ICLR (1)
JMLR (1)
Top co-authors
Research topics
Keywords
federated learning
(6)
distributed training
(3)
distributed learning
(3)
gradient aggregation
(2)
gradient descent
(2)
adversarial perturbation
(2)
byzantine fault tolerance
(2)
byzantine resilience
(2)
convex optimization
(1)
adversarial robustness
(1)
differential privacy
(1)
convergence analysis
(1)
automatic differentiation
(1)
quadratic models
(1)
data augmentation
(1)
stochastic gradient descent
(1)
gradient computation
(1)
geometric analysis
(1)
surrogate loss
(1)
algorithmic stability
(1)
Papers
Scaling Laws for Differentially Private Language Models
ICML 2025
Federated Automatic Differentiation
JMLR 2024
Gradient Descent with Linearly Correlated Noise: Theory and Applications to Differential Privacy
NIPS 2023
Towards Federated Foundation Models: Scalable Dataset Pipelines for Group-Structured Learning
NIPS 2023
Iterated Vector Fields and Conservatism, with Applications to Federated Learning
ALT 2022
Adaptive Federated Optimization
ICLR 2021
Convergence and Accuracy Trade-Offs in Federated Learning and Meta-Learning
AISTATS 2021
On Large-Cohort Training for Federated Learning
NIPS 2021
A Geometric Perspective on the Transferability of Adversarial Directions
AISTATS 2019
Does Data Augmentation Lead to Positive Margin?
ICML 2019
DETOX: A Redundancy-based Framework for Faster and More Robust Gradient Aggregation
NIPS 2019
ATOMO: Communication-efficient Learning via Atomic Sparsification
NIPS 2018
Stability and Generalization of Learning Algorithms that Converge to Global Optima
ICML 2018
DRACO: Byzantine-resilient Distributed Training via Redundant Gradients
ICML 2018