Qi Lyu

alt text 

Ph.D. of Computer Science,
School of EECS,
Oregon State University
Kelley Engineering Center
Corvallis, OR, 97331, US
GitHub

About Me

I obtained my B.S. and M.S. degrees in Electrical Engineering from Fudan University in 2011 and 2014, respectively. Since Sep. 2017, I started my study for Ph.D. degree in Computer Science under the supervision of Prof. Xiao Fu at Oregon State University.

Research Interests

My research interests include:

Publications

  1. Qi Lyu and Xiao Fu, "Provable Subspace Identification Under Post-Nonlinear Mixtures", Neural Information Processing Systems (NeurIPS), 2022. (25.6% [2665/10411])

  2. Qi Lyu and Xiao Fu, "On Finite-Sample Identifiability of Contrastive Learning-Based Nonlinear Independent Component Analysis", International Conference on Machine Learning (ICML), 2022. (21.9% [1235/5630]) [pdf]

  3. Qi Lyu, Xiao Fu, Weiran Wang and Songtao Lu, "Understanding Latent Correlation-Based Multiview Learning and Self-Supervision: An Identifiability Perspective", International Conference on Learning Representations (ICLR), 2022. Spotlight (5.2% [176/3391]) [pdf, code]

  4. Qi Lyu and Xiao Fu, "Finite-Sample Analysis of Deep CCA-Based Unsupervised Post-Nonlinear Multimodal Learning", IEEE Transactions on Neural Networks and Learning Systems, doi: 10.1109/TNNLS.2022.3160407., 2022. [pdf]

  5. Qi Lyu and Xiao Fu, "Identifiability-Guaranteed Simplex-Structured Post-Nonlinear Mixture Learning via Autoencoder", IEEE Transactions on Signal Processing, vol. 69, pp. 4921-4936, 2021. [pdf]

  6. Qi Lyu and Xiao Fu, "Nonlinear Multiview Analysis: Identifiability and Neural Network-Assisted Implementation", IEEE Transactions on Signal Processing, vol. 68, pp. 2697–2712, 2020. [pdf]

  7. Qi Lyu and Xiao Fu, "Nonlinear multiview analysis: Identifiability and neural network-based implementation.", IEEE 11th Sensor Array and Multichannel Signal Processing Workshop (SAM), Jun, 2020. (Best Student Paper Finalist) [pdf]

  8. Qi Lyu and Xiao Fu, "Nonlinear dependent component analysis: Identifiability and algorithm", 28th European Signal Processing Conference (EUSIPCO), Sep, 2020. [pdf]