I am highlighting the following works:
   - Federated learning with only positive labels ICML 2020 [arXiv]
   - Pre-training tasks for embedding-based large-scale retrieval ICLR 2020 [arXiv]
Recent works:
   - Sampled softmax with random Fourier features, NeurIPS 2019 [arXiv]
   - AdaCliP: Adaptive Clipping for Private SGD, [arXiv]
   - Learning a compressed sensing measurement matrix via gradient unrolling, ICML 2019 [arXiv]
   - Stochastic Negative Mining for learning with large output spaces, AISTATS 2019 [arXiv]
Recent works:
   - 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] [Forbes]:

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
Recent works:
   - 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:
   - arXiv:1503.03893: Compact Nonlinear Maps and Circulant Extensions
   - arXiv:1503.00591: Deep Transfer Network: Unsupervised Domain Adaptation
   - arXiv:1502.03436: Fast Neural Networks with Circulant Projections
   - arXiv:1402.5902: On Learning from Label Proportions (v2)
Photo credit: Eileen Barroso

About Me

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. Google Research Google Scholar LinkedIn


Research Interests

Large-scale machine learning:
    Embedding models for fast retrieval
    Learning with large output spaces
    Distributed learning with communication efficiency and differential privacy
    Fast and memory efficient neural networks
    Computer vision applications

Foundations of machine learning:
    Structured matrices
    Random features, dimensionality reduction, binary embedding


Publications

Felix X. Yu, Ankit Singh Rawat, Aditya Krishna Menon, Sanjiv Kumar
Federated learning with only positive labels
ICML 2020 [arXiv]
Wei-Cheng Chang, Felix X. Yu, Yin-Wen Chang, Yiming Yang, Sanjiv Kumar
Pre-training tasks for embedding-based large-scale retrieval
ICLR 2020 [arXiv]
Ankit Singh Rawat, Aditya Krishna Menon, Andreas Veit, Felix X. Yu, Sashank J Reddi, Sanjiv Kumar
Doubly-stochastic mining for heterogeneous retrieval
[arXiv]
Ankit Singh Rawat, Jiecao Chen, Felix X. Yu, Ananda Theertha Suresh, Sanjiv Kumar
Sampled softmax with random Fourier features
NeurIPS 2019 [arXiv]
Shanshan Wu, Alexandros G. Dimakis, Sujay Sanghavi, Felix X. Yu, Daniel Holtmann-Rice, Dmitry Storcheus, Afshin Rostamizadeh, Sanjiv Kumar
Learning a compressed sensing measurement matrix via gradient unrolling
ICML 2019 [arXiv]
Venkatadheeraj Pichapati, Ananda Theertha Suresh, Felix X. Yu, Sashank J Reddi, Sanjiv Kumar
AdaCliP: Adaptive Clipping for Private SGD
[arXiv]
Sashank J. Reddi, Satyen Kale, Felix X. Yu, Dan Holtmann-Rice, Jiecao Chen, Sanjiv Kumar
Stochastic Negative Mining for learning with large output spaces
AISTATS 2019 [arXiv]
Naman Agarwal, Ananda Theertha Suresh, Felix X. Yu, Sanjiv Kumar, H. Brendan McMahan
cpSGD: Communication-efficient and differentially-private distributed SGD
NeurIPS 2018 spotlight [arXiv]
Ian E.H. Yen, Satyen Kale, Felix X. Yu, Daniel Holtmann-Rice, Sanjiv Kumar, Pradeep Ravikumar
Loss decomposition for fast learning in large output spaces
ICML 2018 [PDF]
Xu Zhang, Felix X. Yu, Svebor Karaman, Wei Zhang, Shih-Fu Chang
Heated-up softmax embedding
[arXiv:1809.04157]
Felix X. Yu, Aditya Bhaskara, Sanjiv Kumar, Yunchao Gong, Shih-Fu Chang
On binary embedding using circulant matrices
JMLR 2018 [PDF]
Xiang Wu, Ruiqi Guo, Ananda Theertha Suresh, Sanjiv Kumar, Daniel Holtmann-Rice, David Simcha, Felix X. Yu
Multiscale quantization for fast similarity search
NIPS 2017 [PDF]
Shankar Kumar, Michael Nirschl, Daniel Holtmann-Rice, Hank Liao, Ananda Theertha Suresh, Felix X. Yu
Lattice rescoring strategies for long short term memory language models in speech recognition
ASRU 2017 [arXiv:1711.05448]
Xu Zhang, Felix X. Yu, Sanjiv Kumar, Shih-Fu Chang
Learning spread-out local feature descriptors
ICCV 2017 [PDF] [GitHub]
Ananda Theertha Suresh, Felix X. Yu, Sanjiv Kumar, H. Brendan McMahan
Distributed mean estimation with limited communication
ICML 2017 (acceptance rate 25.5%) [arXiv:1611.00429]
Xu Zhang, Felix X. Yu, Svebor Karaman, Shih-Fu Chang
Learning discriminative and transformation covariant local feature detectors
CVPR 2017 (acceptance rate 29%) [PDF] [GitHub]
Felix X. Yu, Ananda Theertha Suresh, Krzysztof Choromanski, Daniel Holtmann-Rice, Sanjiv Kumar
Orthogonal random features
NIPS 2016 oral (full-length) (acceptance rate 1.8%) [arXiv]
Jakub Konecny, H. Brendan McMahan, Felix X. Yu, Peter Richtarik, Ananda Theertha Suresh, Dave Bacon
Federated Learning: strategies for improving communication efficiency
NIPS 2016 Workshop on Private Multi-Party Machine Learning [arXiv]
Paul Eastham, Andres Munoz, Ashish Sharma, Umar Syed, Sergei Vassilvitskii, Felix Yu
Learning battery consumption of mobile devices
ICML 2016 Workshop on On-device Intelligence [PDF]
Jeffrey Pennington, Felix X. Yu, Sanjiv Kumar
Spherical random features for polynomial kernels
NIPS 2015 spotlight (acceptance rate 4.5%) [PDF] [GitHub]
Felix X. Yu, Sanjiv Kumar, Henry Rowley, Shih-Fu Chang
Compact Nonlinear Maps and circulant extensions
[arXiv:1503.03893]
Xu Zhang, Felix X. Yu, Shih-Fu Chang, Shengjin Wang
Deep Transfer Network: unsupervised domain adaptation
[arXiv:1503.00591]
Felix X. Yu, Yunchao Gong, Sanjiv Kumar
Fast binary embedding for high-dimensional data
Multimedia Data Mining and Analytics: Disruptive Innovation, Springer, 2015
Yu Cheng*, Felix X. Yu*, Rogerio Feris, Sanjiv Kumar, Alok Choudhary, Shih-Fu Chang
An exploration of parameter redundancy in deep networks with circulant projections
ICCV 2015 (acceptance rate 20%) [PDF] [arXiv] [Project]
Xu Zhang, Felix X. Yu, Ruiqi Guo, Sanjiv Kumar, Shengjin Wang, Shih-Fu Chang
Fast orthogonal projection based on Kronecker product
ICCV 2015 (acceptance rate 20%) [PDF] [GitHub] [Project]
Felix X. Yu, Sanjiv Kumar, Yunchao Gong, Shih-Fu Chang
Circulant Binary Embedding
ICML 2014 oral (acceptance rate 25%) [PDF] [arXiv] [GitHub] [Slides] [Project]
Kuan-Ting Lai, Felix X. Yu, Ming-Syan Chen, Shih-Fu Chang
Video event detection by inferring temporal instance labels
CVPR 2014 oral (acceptance rate 5.75%) [PDF] [Project]
Subh Bhattacharya, Felix X. Yu, Shih-Fu Chang
Minimally Needed Evidence for complex event recognition in unconstrained videos
ICMR 2014 oral, best paper award (1/21) (acceptance rate 19%) [PDF]
Tao Chen, Felix X. Yu, Jiawei Chen, Yin Cui, Yan-Ying Chen, Shih-Fu Chang
Object-based visual sentiment concept analysis and application
ACM Multimedia 2014 oral (acceptance rate 20%) [PDF]
Felix X. Yu, Liangliang Cao, Michele Merler, Noel Codella, Tao Chen, John R. Smith, Shih-Fu Chang
Modeling attributes from category-attribute proportions
ACM Multimedia 2014 (Short paper, acceptance rate 30%) [PDF]
Felix X. Yu, Krzysztof Choromanski, Sanjiv Kumar, Tony Jebara, Shih-Fu Chang
On learning from label proportions
[arXiv:1402.5902]
Felix X. Yu, Dong Liu, Sanjiv Kumar, Tony Jebara, Shih-Fu Chang
$\propto$SVM for learning from label proportions
ICML 2013 oral (full-length) (acceptance rate 12%) [PDF] [Supp] [arXiv] [GitHub] [Slides] [Project]
Felix X. Yu, Liangliang Cao, Rogerio S. Feris, John R. Smith, Shih-Fu Chang
Designing category-level attributes for discriminative visual recognition
CVPR 2013 (acceptance rate 25%) [PDF] [Supp] [GitHub] [Poster]
Felix X. Yu, Rongrong Ji, Ming-Hen Tsai, Guangnan Ye, Shih-Fu Chang
Weak attributes for large-scale image retrieval
CVPR 2012 (acceptance rate 24%) [PDF] [Supp] [Poster] [Code] [Project]
Rongrong Ji*, Felix X. Yu*, Tongtao Zhang, Shih-Fu Chang
Active Query Sensing: suggesting the best query view for mobile visual search
TOMCCAP 2012 [Project]
Felix X. Yu, Rongrong Ji, Shih-Fu Chang
Active Query Sensing for mobile location search
ACM Multimedia 2011 oral, best paper award (1/58) (acceptance rate 17%) [Project]