6 citations · 26 across the 9 of their papers we have counts for
9 papers
Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks
Jiayuan Ye, Zhenyu Zhu, Fanghui Liu +2
We analytically investigate how over-parameterization of models in randomized machine learning algorithms impacts the information leakage about their training data. Specifically, w…
Sample Complexity Bounds for Score-Matching: Causal Discovery and Generative Modeling
Zhenyu Zhu, Francesco Locatello, Volkan Cevher
This paper provides statistical sample complexity bounds for score-matching and its applications in causal discovery. We demonstrate that accurate estimation of the score function…
Benign Overfitting in Deep Neural Networks under Lazy Training
Zhenyu Zhu, Fanghui Liu, Grigorios G Chrysos +2
This paper focuses on over-parameterized deep neural networks (DNNs) with ReLU activation functions and proves that when the data distribution is well-separated, DNNs can achieve B…
Robust Failure Diagnosis of Microservice System through Multimodal Data
Shenglin Zhang, Pengxiang Jin, Zihan Lin +10
Automatic failure diagnosis is crucial for large microservice systems. Currently, most failure diagnosis methods rely solely on single-modal data (i.e., using either metrics, logs,…
Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study
Yongtao Wu, Zhenyu Zhu, Fanghui Liu +2
Neural tangent kernel (NTK) is a powerful tool to analyze training dynamics of neural networks and their generalization bounds. The study on NTK has been devoted to typical neural…
Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization)
Zhenyu Zhu, Fanghui Liu, Grigorios G Chrysos +1
We study the average robustness notion in deep neural networks in (selected) wide and narrow, deep and shallow, as well as lazy and non-lazy training settings. We prove that in the…
Generalization Properties of NAS under Activation and Skip Connection Search
Zhenyu Zhu, Fanghui Liu, Grigorios G Chrysos +1
Neural Architecture Search (NAS) has fostered the automatic discovery of state-of-the-art neural architectures. Despite the progress achieved with NAS, so far there is little atten…
Controlling the Complexity and Lipschitz Constant improves polynomial nets
Zhenyu Zhu, Fabian Latorre, Grigorios G Chrysos +1
While the class of Polynomial Nets demonstrates comparable performance to neural networks (NN), it currently has neither theoretical generalization characterization nor robustness…
PSDNet and DPDNet: Efficient channel expansion, Depthwise-Pointwise-Depthwise Inverted Bottleneck Block
Guoqing Li, Meng Zhang, Qianru Zhang +7
In many real-time applications, the deployment of deep neural networks is constrained by high computational cost and efficient lightweight neural networks are widely concerned. In…