no code implementations • 26 Jan 2024 • Girish Kumar, Thomas Strohmer, Roman Vershynin
Much of the research in differential privacy has focused on offline applications with the assumption that all data is available at once.
1 code implementation • 13 Jan 2024 • Shizhou Xu, Thomas Strohmer
Furthermore, when there exists a conflict between the two, we first relax the former to the Pareto frontier (or equivalently the optimal trade-off) between $L^2$ error and statistical disparity, and then analyze the compatibility between the frontier and the individual fairness requirements.
no code implementations • 26 May 2023 • Yiyun He, Thomas Strohmer, Roman Vershynin, Yizhe Zhu
Differentially private synthetic data provide a powerful mechanism to enable data analysis while protecting sensitive information about individuals.
no code implementations • 24 May 2022 • JunDa Sheng, Thomas Strohmer
The stochastic block model is a canonical random graph model for clustering and community detection on network-structured data.
1 code implementation • 2 Jan 2022 • Shizhou Xu, Thomas Strohmer
Numerical simulations underscore the advantages: (1) the pre-processing step is compositive with arbitrary conditional expectation estimation supervised learning methods and unseen data; (2) the fair representation protects the sensitive information by limiting the inference capability of the remaining data with respect to the sensitive data; (3) the optimal affine maps are computationally efficient even for high-dimensional data.
no code implementations • ICLR 2022 • Matthew Thorpe, Tan Minh Nguyen, Hedi Xia, Thomas Strohmer, Andrea Bertozzi, Stanley Osher, Bao Wang
We propose GRAph Neural Diffusion with a source term (GRAND++) for graph deep learning with a limited number of labeled nodes, i. e., low-labeling rate.
no code implementations • 10 Jul 2020 • March Boedihardjo, Shaofeng Deng, Thomas Strohmer
The two-step spectral clustering method, which consists of the Laplacian eigenmap and a rounding step, is a widely used method for graph partitioning.
no code implementations • 21 Apr 2020 • Shaofeng Deng, Shuyang Ling, Thomas Strohmer
We study the performance of classical two-step spectral clustering via the graph Laplacian to learn the stochastic block model.
no code implementations • NeurIPS Workshop Deep_Invers 2019 • Yang Li, Thomas Strohmer
By processing the data on the device that has collected the data, we can dramatically increase the level of privacy.
no code implementations • 4 Sep 2019 • Yang Li, Thomas Strohmer
We propose a hybrid hardware-software framework that has the potential to significantly reduce the computational complexity and memory requirements of on-device machine learning.
no code implementations • 29 Jun 2018 • Shuyang Ling, Thomas Strohmer
This paper is devoted to the theoretical foundations of spectral clustering and graph cuts.
1 code implementation • 15 Jun 2016 • XiaoDong Li, Shuyang Ling, Thomas Strohmer, Ke Wei
To the best of our knowledge, our algorithm is the first blind deconvolution algorithm that is numerically efficient, robust against noise, and comes with rigorous recovery guarantees under certain subspace conditions.
Information Theory Information Theory