- cpSGD: Communication-efficient and differentially-private distributed SGD, NIPS 2018 spotlight [arXiv
- Heated-up softmax embedding, [arXiv:1809.04157
- Loss decomposition for fast learning in large output spaces, ICML 2018 [PDF
- Multiscale quantization for fast similarity search, NIPS 2017 [PDF
- Lattice rescoring strategies for long short term memory language models in speech recognition, ASRU 2017 [arXiv
- Learning spread-out local feature descriptors, ICCV 2017 [PDF
- On binary embedding using circulant matrices, JMLR [PDF
• A Google research blog post was released on communication efficient Federated Learning [Google blog
Federated Learning enables mobile phones to collaboratively learn a shared prediction model while keeping all the training data on device... We developed a novel way to reduce upload communication costs up to 100x by compressing updates using random rotations and quantization.
• The paper summarizing the quantization approach used in Federated Learning, distributed mean estimation with limited communication
, is accepted at ICML 2017 [arXiv
• Learning discriminative and transformation covariant local feature detectors
accepted at CVPR 2017
• Named outstanding reviewer of NIPS 2016
- Orthogonal random features
accepted as full oral presentation at NIPS 2016 [arXiv
- Distributed mean estimation with limited communication [arXiv
- Federated Learning: strategies for improving communication efficiency [arXiv
- Learning battery consumption of mobile devices [pdf
Co-organized workshop and conference:
- NIPS 2015 Workshop
Learning and Privacy with Incomplete Data and Weak Supervision.
- International Conference on Multimedia Retrieval (ICMR) 2016
I defended my PhD, and joined Google Research in June 2015.
Recently accepted papers:
- NIPS 2015 (Spotlight): Spherical Random Features for Polynomial Kernels
- ICCV 2015: An Exploration of Parameter Redundancy in Deep Networks with Circulant Projections
- ICCV 2015: Fast Orthogonal Projection Based on Kronecker Product
Recent ongoing works available on arXiv:
: Compact Nonlinear Maps and Circulant Extensions
: Deep Transfer Network: Unsupervised Domain Adaptation
: Fast Neural Networks with Circulant Projections
: On Learning from Label Proportions (v2)
Photo credit: Eileen Barroso
Felix X. Yu is a Research Scientist at Google, New York.
He is currently working on large-scale machine learning.
Felix received his Ph.D from
Dept. of Electrical Engineering, Columbia University, in 2015, and his B.S. from
Dept. of Electronic Engineering, Tsinghua University, China, in 2010.
Large-scale machine learning:
Distributed learning with communication efficiency and differential privacy
Learning with large output space
Fast and memory efficient neural networks
Computer vision applications
Foundations of machine learning:
Random features, dimensionality reduction, binary embedding