Sotabase

Career

· Founding Director of the Responsible AI Initiative, UC Berkeley Artificial Intelligence Research Lab (BAIR)2024–
· Postdoctoral Researcher, UC Berkeley2017–
· PhD in Computer Science, UC Berkeley2012–2017
· Courtesy faculty member in Electrical and Computer Engineering, UC Berkeley

Publications (55)

LEAF: A Benchmark for Federated Settings
arXiv.org · 2018
1,643
cited
A Field Guide to Federated Optimization
arXiv.org · 2021
465
cited
Communication-Efficient Distributed Dual Coordinate Ascent
Neural Information Processing Systems · 2014
357
cited
One-Shot Federated Learning
arXiv.org · 2019
244
cited
A Kernel Theory of Modern Data Augmentation
International Conference on Machine Learning · 2018
208
cited
MLI: An API for Distributed Machine Learning
2013 IEEE 13th International Conference on Data Mining · 2013
206
cited
Clean: A History of Personal Hygiene and Purity
2007
145
cited
Diverse Client Selection for Federated Learning via Submodular Maximization
International Conference on Learning Representations · 2022
132
cited
Learning Context-Aware Policies from Multiple Smart Homes via Federated Multi-Task Learning
International Conference on Internet-of-Things Design and Implementation · 2020
103
cited
RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold
Neural Information Processing Systems · 2024
99
cited
On Privacy and Personalization in Cross-Silo Federated Learning
Neural Information Processing Systems · 2022
70
cited
Privacy for Free: Communication-Efficient Learning with Differential Privacy Using Sketches
arXiv.org · 2019
61
cited
Motley: Benchmarking Heterogeneity and Personalization in Federated Learning
arXiv.org · 2022
53
cited
Plumber: Diagnosing and Removing Performance Bottlenecks in Machine Learning Data Pipelines
Conference on Machine Learning and Systems · 2021
38
cited
e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs
arXiv.org · 2025
37
cited
Federated Kernelized Multi-Task Learning
2018
29
cited
Diverse Client Selection for Federated Learning: Submodularity and Convergence Analysis
2021
27
cited
MLSys: The New Frontier of Machine Learning Systems
2019
25
cited
Adversarial Unlearning: Reducing Confidence Along Adversarial Directions
Neural Information Processing Systems · 2022
24
cited
SysML: The New Frontier of Machine Learning Systems
arXiv.org · 2019
23
cited
Sotabase
Virginia Smith | Researcher Profile | Sotabase | Sotabase