Afshin Rostamizadeh
Afshin is a research scientist at Google Research NY, where he specializes in designing and applying machine learning algorithms. He received his BS in Electrical Engineering and Computer Science from UC Berkeley, his PhD in Computer Science from the Courant Institute at NYU with advisor Mehryar Mohri and was a post-doc at UC Berkeley in Peter Bartlett's group.
He has worked on problems such as learning from non-iid samples, learning from biased samples, learning from data with missing features and automatic kernel selection for kernelized algorithms such as SVM.
Authored Publications
Sort By
Google
DistillSpec: Improving speculative decoding via knowledge distillation
Yongchao Zhou
Kaifeng Lyu
Aditya Menon
Jean-François Kagy
International Conference on Learning Representations (ICLR) (2024)
Batch Active Learning at Scale
Anand Rajagopalan
Gui Citovsky
Laz Karydas
NeurIPS 2021
Understanding the Effects of Batching in Online Active Learning
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (2020)
A System for Massively Parallel Hyperparameter Tuning
Liam Li
Kevin Jamieson
Ekaterina Gonina
Jonathan Ben-tzur
Moritz Hardt
Benjamin Recht
Ameet Talwalkar
Third Conference on Systems and Machine Learning (2020) (to appear)
An Analysis of SVD for Deep Rotation Estimation
Jake Levinson
Arthur Chen
Angjoo Kanazawa
Advances in Neural Information Processing Systems (NeurIPS) 2020
Learning a Compressed Sensing Measurement Matrix via Gradient Unrolling
Shanshan Wu
Alexandros G. Dimakis
Sujay Sanghavi
Daniel Holtmann-Rice
Dmitry Storcheus
ICML (2019)
