Zhenyu LIAO

Work

Huazhong University of Science and Technology
|

Associate Professor

China

→

University of California Berkeley
|

Postdoctoral Scholar

US

→

Education

Université Paris-Saclay
France

→

Ph. D.

Université Paris-Saclay
France

→

M. Sc.

Huazhong University of Science and Technology
China

→

B.E.

Publications

Subspace Collision: An Efficient and Accurate Framework for High-dimensional Approximate Nearest Neighbor Search

Published by

Proceedings of the ACM on Management of Data

Summary

journal-article

Robust and Communication-Efficient Federated Domain Adaptation via Random Features

Published by

IEEE Transactions on Knowledge and Data Engineering

Summary

journal-article

An Achievable and Analytic Solution to Information Bottleneck for Gaussian Mixtures

Published by

2024 IEEE International Symposium on Information Theory (ISIT)

Summary

conference-paper

FedRF-Adapt: Robust and Communication-Efficient Federated Domain Adaptation via Random Features

Published by

2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)

Summary

conference-paper

Robustness of random-control quantum-state tomography

Published by

Physical Review A

Summary

journal-article

A geometric approach of gradient descent algorithms in linear neural networks

Published by

Mathematical Control and Related Fields

Summary

journal-article

Random Matrix Methods for Machine Learning

Published by

Cambridge University Press

Summary

book

Kernel regression in high dimensions: Refined analysis beyond double descent

Published by

Proceedings of Machine Learning Research

Summary

journal-article

A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent*

Published by

Journal of Statistical Mechanics: Theory and Experiment

Summary

journal-article

Kernel regression in high dimensions: Refined analysis beyond double descent

Published by

Proceedings of Machine Learning Research

Summary

journal-article

A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent

Published by

Journal of Statistical Mechanics: Theory and Experiment

Summary

journal-article

Hessian eigenspectra of more realistic nonlinear models

Published by

arXiv

Summary

other

Random matrices in service of ML footprint: Ternary random features with no performance loss

Published by

arXiv

Summary

other

Sparse Quantized Spectral Clustering

Published by

International Conference on Learning Representations

Summary

conference-paper

Precise expressions for random projections: Low-rank approximation and randomized Newton

Published by

arXiv

Summary

other

Sparse sketches with small inversion bias

Published by

arXiv

Summary

other

Sparse quantized spectral clustering

Published by

arXiv

Summary

other

A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent

Published by

The 34th Conference on Neural Information Processing Systems (NeurIPS'20)

Summary

conference-paper

A random matrix analysis of random fourier features: Beyond the Gaussian kernel, a precise phase Transition, and the corresponding double descent

Published by

arXiv

Summary

other

A random matrix analysis of random Fourier features: Beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent

Published by

Advances in Neural Information Processing Systems

Summary

conference-paper

High Dimensional Classification via Regularized and Unregularized Empirical Risk Minimization: Precise Error and Optimal Loss

Published by

ArXiv

Summary

journal-article

Kernel regression in high dimensions: Refined analysis beyond double descent

Published by

arXiv

Summary

other

Precise expressions for random projections: Low-rank approximation and randomized Newton

Published by

The 34th Conference on Neural Information Processing Systems (NeurIPS'20)

Summary

conference-paper

Precise expressions for random projections: Low-rank approximation and randomized Newton

Published by

Advances in Neural Information Processing Systems

Summary

conference-paper

High Dimensional Classification via Empirical Risk Minimization: Improvements and Optimality

Summary

journal-article

A Large Dimensional Analysis of Least Squares Support Vector Machines

Published by

IEEE Transactions on Signal Processing

Summary

journal-article

A Large Dimensional Analysis of Least Squares Support Vector Machines

Published by

IEEE Transactions on Signal Processing

Summary

journal-article

A Large Dimensional Analysis of Least Squares Support Vector Machines

Published by

IEEE Transactions on Signal Processing

Summary

journal-article

A Geometric Approach of Gradient Descent Algorithms in Neural Networks

Summary

journal-article

A Large Scale Analysis of Logistic Regression: Asymptotic Performance and New Insights

Published by

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP'19)

Summary

conference-paper

A Large Scale Analysis of Logistic Regression: Asymptotic Performance and New Insights

Published by

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Summary

conference-paper

A LARGE SCALE ANALYSIS OF LOGISTIC REGRESSION: ASYMPTOTIC PERFORMANCE AND NEW INSIGHTS

Published by

IEEE International Conference on Acoustics, Speech, and Signal Processing

Summary

conference-paper

High Dimensional Classification Via Empirical Risk Minimization: Improvements and Optimality

Published by

arXiv

Summary

other

Inner-product Kernels are Asymptotically Equivalent to Binary Discrete Kernels

Summary

journal-article

Inner-product kernels are asymptotically equivalent to binary discrete kernels

Published by

arXiv

Summary

other

Inner-product Kernels are Asymptotically Equivalent to Binary Discrete Kernels

Published by

ArXiv

Summary

journal-article

On Inner-Product Kernels of High Dimensional Data

Published by

IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP'19)

Summary

conference-paper

ON INNER-PRODUCT KERNELS OF HIGH DIMENSIONAL DATA

Published by

IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing

Summary

conference-paper

The dynamics of learning: A random matrix approach

Published by

arXiv

Summary

other

On the Spectrum of Random Features Maps of High Dimensional Data

Published by

Proceedings of the 35th International Conference on Machine Learning (ICML'18)

Summary

conference-paper

On the spectrum of random features maps of high dimensional data

Published by

arXiv

Summary

other

On the Spectrum of Random Features Maps of High Dimensional Data

Published by

Proceedings of Machine Learning Research

Summary

journal-article

A random matrix approach to neural networks

Published by

Annals of Applied Probability

Summary

journal-article

The Dynamics of Learning: A Random Matrix Approach

Published by

Proceedings of the 35th International Conference on Machine Learning (ICML'18)

Summary

conference-paper

The Dynamics of Learning: A Random Matrix Approach

Published by

Proceedings of Machine Learning Research

Summary

journal-article

A Random Matrix Approach to Neural Networks

Published by

The Annals of Applied Probability

Summary

journal-article

A geometric approach of gradient descent algorithms in linear neural networks

Published by

arXiv

Summary

other

A RANDOM MATRIX APPROACH TO NEURAL NETWORKS

Published by

Annals of Applied Probability

Summary

journal-article

Classification Asymptotics in the Random Matrix Regime

Published by

The 26th European Signal Processing Conference (EUSIPCO'18)

Summary

conference-paper

Classification asymptotics in the random matrix regime

Published by

European Signal Processing Conference

Summary

conference-paper

CLASSIFICATION ASYMPTOTICS IN THE RANDOM MATRIX REGIME

Published by

European Signal Processing Conference

Summary

conference-paper

Random Matrices Meet Machine Learning: A Large Dimensional Analysis of LS-SVM

Published by

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP'17)

Summary

conference-paper

Random matrices meet machine learning: A large dimensional analysis of LS-SVM

Published by

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Summary

conference-paper

RANDOM MATRICES MEET MACHINE LEARNING: A LARGE DIMENSIONAL ANALYSIS OF LS-SVM

Published by

IEEE International Conference on Acoustics, Speech, and Signal Processing

Summary

conference-paper

A large dimensional analysis of least squares support vector machines

Published by

arXiv

Summary

other

A random matrix approach to neural networks

Published by

arXiv

Summary

other

A large dimensional analysis of least squares support vector machines

Published by

arXiv

Summary

other