Publications
Conference papers
Y. Liu, Z. Liao .
“Dual-Attention Convolution Experts for Sparse Tensor Completion .” European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases - Research Track (ECML PKDD) (2026).
C. Yaakoubi, C. Louart, M. Tiomoko, Z. Liao .
“Characterization of Gaussian Universality Breakdown in High-Dimensional Empirical Risk Minimization .” Proceedings of the 43rd International Conference on Machine Learning (ICML) (2026).
J. Bai, D. Yu, Z. Liao , T. Hou, F. Zhou, R. C. Qiu, Z. Ling.
“Diving into Kronecker Adapters: Component Design Matters .” Proceedings of the 43rd International Conference on Machine Learning (ICML) (2026).
Y. Xu, S. Zhang, G. Zhou, Z. Liao .
“Optimal Large-scale Finite-horizon Optimization via Random Matrix Theory.” 2026 34th European Signal Processing Conference (EUSIPCO) (2026).
C. Louart, Z. Liao , M. Tiomoko.
“A Conditional-Gaussian View of Score Universality Through Low-Dimensional Statistics.” 2026 IEEE International Symposium on Information Theory Workshops (ISIT-W) (2026).
Y. Xu, Z. Liao .
“New Characterizations of Deep Neural Networks Beyond the Ultra-Wide Regime.” 2026 IEEE International Symposium on Information Theory Workshops (ISIT-W) (2026).
Y. Xu, Z. Liao .
“An Improved Convergence Analysis of Gossip Methods for Large Random Graphs .” ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , 22562-22566 (2026).
Y. Moahker, M. Tiomoko, C. Louart, Z. Liao .
“A Random Matrix Perspective of Echo State Networks: From Precise Bias-Variance Characterization to Optimal Regularization .” ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , 20716-20720 (2026). [poster ]
J. Wei, Z. Liao , R. Han, Q. Xu, C. Yang, T. Palpanas.
“TaCo: Data-adaptive and Query-aware Subspace Collision for High-dimensional Approximate Nearest Neighbor Search .” Proc. ACM Manag. Data (SIGMOD) , 4 (3) (2026). [preprint ]
C. Niu, Z. Liao , Z. Ling, M. W. Mahoney.
“Fundamental Bias in Inverting Random Sampling Matrices with Application to Sub-sampled Newton .” Proceedings of the 42nd International Conference on Machine Learning (ICML) , 267 , 46649–46692 (2025). (Oral ) [preprint ]
X. Mai, Z. Liao .
“The Breakdown of Gaussian Universality in Classification of High-dimensional Mixtures .” International Conference on Learning Representations (ICLR) (2025). [preprint ] [slides ]
J. Wei, X. Lee, Z. Liao , T. Palpanas, B. Peng.
“Subspace Collision: An Efficient and Accurate Framework for High-dimensional Approximate Nearest Neighbor Search .” Proc. ACM Manag. Data (SIGMOD) , 3 (1) (2025). [preprint ]
W. Yang, Z. Wang, X. Mai, Z. Ling, R. C. Qiu, Z. Liao .
“Inconsistency of ESPRIT DoA Estimation for Large Arrays and a Correction via RMT .” 2024 32nd European Signal Processing Conference (EUSIPCO) , 2722–2726 (2024). (Best Student Paper Candidate ) [here ]
Z. Ling, L. Li, Z. Feng, Y. Zhang, F. Zhou, R. C. Qiu, Z. Liao .
“Deep Equilibrium Models Are Almost Equivalent to Not-so-deep Explicit Models for High-dimensional Gaussian Mixtures .” Proceedings of the 41st International Conference on Machine Learning (ICML) , 235 , 30585–30609 (2024). [preprint ]
Y. Song, K. Wan, Z. Liao , H. Xu, G. Caire, S. Shamai.
“An Achievable and Analytic Solution to Information Bottleneck for Gaussian Mixtures .” 2024 IEEE International Symposium on Information Theory (ISIT) , 2460–2465 (2024).
Y. Wang, Z. Feng, Z. Liao .
“FedRF-Adapt: Robust and Communication-Efficient Federated Domain Adaptation via Random Features .” 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) , 615–619 (2024). [workshop on timely and private machine learning over networks ]
L. Gu, Y. Du, Y. Zhang, D. Xie, S. Pu, R. Qiu, Z. Liao .
“"Lossless" Compression of Deep Neural Networks: A High-dimensional Neural Tangent Kernel Approach .” Advances in Neural Information Processing Systems (NeurIPS) , 35 , 3774–3787 (2022). (Spotlight ) [preprint ]
H. T. Ali, Z. Liao , R. Couillet.
“Random matrices in service of ML footprint: ternary random features with no performance loss .” International Conference on Learning Representations (ICLR) (2022). [preprint ]
Z. Liao , M. W. Mahoney.
“Hessian Eigenspectra of More Realistic Nonlinear Models .” Advances in Neural Information Processing Systems (NeurIPS) , 34 , 20104–20117 (2021). (Oral ) [preprint ]
M. Derezinski, Z. Liao , E. Dobriban, M. Mahoney.
“Sparse sketches with small inversion bias .” Proceedings of Thirty Fourth Conference on Learning Theory (COLT) , 134 , 1467–1510 (2021). [preprint ]
Z. Liao , R. Couillet, M. W. Mahoney.
“Sparse Quantized Spectral Clustering .” International Conference on Learning Representations (ICLR) (2021). (Spotlight ) [poster ] [slides ] [preprint ]
F. Liu, Z. Liao , J. Suykens.
“Kernel Regression in High Dimension: Refined Analysis beyond Double Descent .” Proceedings of The 24th International Conference on Artificial Intelligence and Statistics (AISTATS) , 130 , 649–657 (2021). [preprint ]
Z. Liao , R. Couillet, M. W. Mahoney.
“A Random Matrix Analysis of Random Fourier Features: Beyond the Gaussian Kernel, A Precise Phase Transition, and the Corresponding Double Descent .” Advances in Neural Information Processing Systems (NeurIPS) , 33 , 13939–13950 (2020). [preprint ]
M. Derezinski, F. T. Liang, Z. Liao , M. W. Mahoney.
“Precise expressions for random projections: Low-rank approximation and randomized Newton .” Advances in Neural Information Processing Systems (NeurIPS) , 33 , 18272–18283 (2020).
Z. Liao , R. Couillet.
“On Inner-Product Kernels of High Dimensional Data .” 2019 IEEE 8th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP) , 579–583 (2019). [preprint ]
X. Mai, Z. Liao , R. Couillet.
“A Large Scale Analysis of Logistic Regression: Asymptotic Performance and New Insights .” IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , 3357–3361 (2019). [poster ] [preprint ]
R. Couillet, Z. Liao , X. Mai.
“Classification Asymptotics in the Random Matrix Regime .” The 26th European Signal Processing Conference (EUSIPCO) , 1875–1879 (2018). [preprint ]
Z. Liao , R. Couillet.
“The Dynamics of Learning: A Random Matrix Approach .” Proceedings of the 35th International Conference on Machine Learning (ICML) , 80 , 3072–3081 (2018). (Long Talk ) [slides ] [preprint ]
Z. Liao , R. Couillet.
“On the Spectrum of Random Features Maps of High Dimensional Data .” Proceedings of the 35th International Conference on Machine Learning (ICML) , 80 , 3063–3071 (2018). (Long Talk ) [slides ] [preprint ]
Z. Liao , R. Couillet.
“Random Matrices Meet Machine Learning: A Large Dimensional Analysis of LS-SVM .” IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , 2397–2401 (2017). [slides ] [preprint ]
Journal papers
Z. Liao , M. W. Mahoney.
“Random Matrix Theory for Deep Learning: Beyond Eigenvalues of Linear Models .” IEEE Signal Processing Magazine , 43 (2), 93-106 (2026). [preprint ]
Z. Wang, W. Yang, X. Mai, Z. Ling, Z. Liao , R. C. Qiu.
“A Large-Dimensional Analysis of ESPRIT DoA Estimation: Inconsistency and a Correction via RMT .” IEEE Transactions on Signal Processing , 74 , 2290–2303 (2026). [preprint ]
Z. Feng, Y. Wang, J. Li, F. Yang, J. Lou, T. Mi, R. C. Qiu, Z. Liao .
“Robust and Communication-Efficient Federated Domain Adaptation via Random Features .” IEEE Transactions on Knowledge and Data Engineering , 37 (3), 1411-1424 (2025). [preprint ] [code ]
J. Wang, S. Zhang, J. Cai, Z. Liao , C. Arenz, R. Betzholz.
“Robustness of random-control quantum-state tomography .” Phys. Rev. A , 108 (2), 022408 (2023). [preprint ]
Y. Chitour, Z. Liao , R. Couillet.
“A geometric approach of gradient descent algorithms in linear neural networks .” Mathematical Control and Related Fields , 13 (3), 918-945 (2023). [preprint ]
Z. Liao , R. Couillet, M. W. Mahoney.
“A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent .” Journal of Statistical Mechanics: Theory and Experiment , 2021 (12), 124006 (2021). [preprint ]
Z. Liao , R. Couillet.
“A Large Dimensional Analysis of Least Squares Support Vector Machines .” IEEE Transactions on Signal Processing , 67 (4), 1065–1074 (2019). [preprint ] [supplementary material ]
C. Louart, Z. Liao , R. Couillet.
“A Random Matrix Approach to Neural Networks .” The Annals of Applied Probability , 28 (2), 1190–1248 (2018). [preprint ]
Preprints
C. Niu, S. Garg, M. Derezinski, Z. Liao .
“Debiasing Random Oblique Projections for Subsampled OLS and Fast CUR in High Dimensions .” (2026).
S. Li, T. Hou, Z. Liao , T. Gao.
“Latent Iterative Refinement Flow: A Geometric Constrained Approach for Limited-Data Generation .” (2026).
Z. Liao , J. Liu, T. Hou, D. Zou, Z. Ling.
“On the Interpolation Error of Nonlinear Attention versus Linear Regression .” (2025).
J. Lin, Z. Ling, Z. Feng, J. Xu, M. Liao, F. Zhou, T. Hou, Z. Liao , R. C. Qiu.
“IGNN-Solver: A Graph Neural Solver for Implicit Graph Neural Networks .” (2025).
Z. Liao , Y. Xia, C. Niu, Y. Xiao.
“Analysis and Approximate Inference of Large Random Kronecker Graphs .” (2024).
Y. Du, Z. Ling, R. C. Qiu, Z. Liao .
“High-dimensional Learning Dynamics of Deep Neural Nets in the Neural Tangent Regime .” High-dimensional Learning Dynamics Workshop, The Fortieth International Conference on Machine Learning (ICML) (2023). [high-dimensional learning dynamics workshop ]
Z. Ling, Z. Liao , R. C. Qiu.
“On the Equivalence Between Implicit and Explicit Neural Networks: A High-dimensional Viewpoint .” Proceedings of HiLD: High-dimensional Learning Dynamics Workshop, The Fortieth International Conference on Machine Learning (ICML) (2023). [high-dimensional learning dynamics workshop ]
X. Mai, Z. Liao .
“High Dimensional Classification via Regularized and Unregularized Empirical Risk Minimization: Precise Error and Optimal Loss .” arXiv preprint arXiv:1905.13742 (2020).
Z. Liao , R. Couillet.
“Inner-product Kernels are Asymptotically Equivalent to Binary Discrete Kernels .” (2019).
Ph.D. thesis
Z. Liao .
“A random matrix framework for large dimensional machine learning and neural networks .” (2019). [slides ]