Zhenyu Liao
17 papers · 2018–2025 · 9 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π Interdisciplinary Bridge π§ Keyword Pioneer π Academic Marathon (7) π Cross-Pollinator (12)
πΊοΈ
Taxonomy Completionist
(28)
π
Conference Polyglot
(9)
π
Century Club
(17)
ποΈ
Keyword Collector
(62)
β‘
Prolific Year
(5)
Conferences
ICML (4)
NIPS (4)
ICLR (3)
AISTATS (1)
COLT (1)
CVPR (1)
ECCV (1)
IJCAI (1)
JMLR (1)
Top co-authors
Keywords
random matrix
(3)
spectral analysis
(3)
kernel methods
(2)
double descent
(2)
matrix sketching
(2)
model compression
(2)
random matrix theory
(2)
low-rank approximation
(1)
numerical optimization
(1)
neural tangent kernel
(1)
incremental learning
(1)
signal processing
(1)
sparse representation
(1)
gradient descent
(1)
post-training quantization
(1)
kernel ridge regression
(1)
matrix factorization
(1)
kernel matrix
(1)
inverse covariance
(1)
high-dimensional analysis
(1)
Papers
The Breakdown of Gaussian Universality in Classification of High-dimensional Linear Factor Mixtures
ICLR 2025
ECC-SNN: Cost-Effective Edge-Cloud Collaboration for Spiking Neural Networks
IJCAI 2025
Fundamental Bias in Inverting Random Sampling Matrices with Application to Sub-sampled Newton
ICML 2025
Deep Equilibrium Models are Almost Equivalent to Not-so-deep Explicit Models for High-dimensional Gaussian Mixtures
ICML 2024
Random matrices in service of ML footprint: ternary random features with no performance loss
ICLR 2022
"Lossless" Compression of Deep Neural Networks: A High-dimensional Neural Tangent Kernel Approach
NIPS 2022
Hessian Eigenspectra of More Realistic Nonlinear Models
NIPS 2021
Kernel regression in high dimensions: Refined analysis beyond double descent
AISTATS 2021
Sparse Quantized Spectral Clustering
ICLR 2021
Sparse sketches with small inversion bias
COLT 2021
Complete Dictionary Learning via L4-Norm Maximization over the Orthogonal Group
JMLR 2020
Precise expressions for random projections: Low-rank approximation and randomized Newton
NIPS 2020
AdaBits: Neural Network Quantization With Adaptive Bit-Widths
CVPR 2020
Regional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against Defenses
ECCV 2020
A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent
NIPS 2020
On the Spectrum of Random Features Maps of High Dimensional Data
ICML 2018
The Dynamics of Learning: A Random Matrix Approach
ICML 2018