Federated learning with only positive labels, ICML 2020 [arXiv]
Pre-training tasks for embedding-based large-scale retrieval, ICLR 2020 [arXiv]
Learning discrete distributions: user-lever vs item-level privacy, NeurIPS 2020 [arXiv]
Semantic label smoothing for sequence to sequence problems, EMNLP 2020 [arXiv]
Pre-training tasks for embedding-based large-scale retrieval, ICLR 2020 [arXiv]
Learning discrete distributions: user-lever vs item-level privacy, NeurIPS 2020 [arXiv]
Semantic label smoothing for sequence to sequence problems, EMNLP 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]
- 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]
- 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]:
• Learning discriminative and transformation covariant local feature detectors accepted at CVPR 2017
• Named outstanding reviewer of NIPS 2016
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.
- 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
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
- 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
Yuhan Liu, Ananda Theertha Suresh, Felix X. Yu, Sanjiv Kumar, Michael Riley Learning discrete distributions: user-lever vs item-level privacy NeurIPS 2020 [arXiv]
Michal Lukasik, Himanshu Jain, Aditya Krishna Menon, Seungyeon Kim, Srinadh Bhojanapalli, Felix X. Yu, Sanjiv Kumar Semantic label smoothing for sequence to sequence problems
EMNLP 2020 [arXiv]
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]