Sotabase

Career

· Professor, University of California, Berkeley2013–
· Amazon Scholar, Amazon
· Vice President and Director of the Big Data Group, International Computer Science Institute (ICSI)
· Group Lead for the Machine Learning and Analytics Group, Lawrence Berkeley National Laboratory
· Professor, Stanford University
· Researcher/Faculty, Yahoo Research
· Ph.D. in Computational Statistical Mechanics, Yale University
· Professor, Yale University

Publications (84)

A Survey of Quantization Methods for Efficient Neural Network Inference
Low-Power Computer Vision · 2021
1,390
cited
Characterizing possible failure modes in physics-informed neural networks
Neural Information Processing Systems · 2021
917
cited
HAWQ: Hessian AWare Quantization of Neural Networks With Mixed-Precision
IEEE International Conference on Computer Vision · 2019
607
cited
ZeroQ: A Novel Zero Shot Quantization Framework
Computer Vision and Pattern Recognition · 2020
462
cited
I-BERT: Integer-only BERT Quantization
International Conference on Machine Learning · 2021
412
cited
ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning
AAAI Conference on Artificial Intelligence · 2020
345
cited
HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks
Neural Information Processing Systems · 2019
338
cited
SqueezeLLM: Dense-and-Sparse Quantization
International Conference on Machine Learning · 2023
268
cited
Shallow neural networks for fluid flow reconstruction with limited sensors
Proceedings of the Royal Society A · 2020
255
cited
A Fast Post-Training Pruning Framework for Transformers
Neural Information Processing Systems · 2022
206
cited
Neurotoxin: Durable Backdoors in Federated Learning
International Conference on Machine Learning · 2022
187
cited
Speculative Decoding with Big Little Decoder
Neural Information Processing Systems · 2023
166
cited
Full Stack Optimization of Transformer Inference: a Survey
arXiv.org · 2023
152
cited
Squeezeformer: An Efficient Transformer for Automatic Speech Recognition
Neural Information Processing Systems · 2022
132
cited
Lipschitz Recurrent Neural Networks
International Conference on Learning Representations · 2020
124
cited
Improving Semi-supervised Federated Learning by Reducing the Gradient Diversity of Models
2021 IEEE International Conference on Big Data (Big Data) · 2021
104
cited
Determinantal Point Processes in Randomized Numerical Linear Algebra
Notices of the American Mathematical Society · 2020
91
cited
HAWQV3: Dyadic Neural Network Quantization
International Conference on Machine Learning · 2020
91
cited
ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training
International Conference on Machine Learning · 2021
89
cited
Hessian-Aware Pruning and Optimal Neural Implant
IEEE Workshop/Winter Conference on Applications of Computer Vision · 2021
75
cited
Sotabase