Differentially Private Clustering in High-Dimensional Euclidean Spaces
By Maria-Florina Balcan, Travis Dick, Yingyu Liang, Wenlong Mou, Hongyang Zhang. 2017
92 citations recorded by the source corpus.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Jayadev Acharya
- Badih Ghazi
- Ziteng Sun
- Gautam Kamath
- Ravi Kumar
- Peter Kairouz
- Pasin Manurangsi
- Alisa Chang
Citations in the corpus
- The Power of the Hybrid Model for Mean Estimation (2018, methodology): “Other DP K-means algorithms exist in both the TCM [4, 8, 43, 46, 48, 53] and LM [47, 52, 54, 57] which improve on our two non-hybrid K-means algorithms.”
- INSPECTRE: Privately Estimating the Unseen (2018, background): “A number of other problems have been studied with privacy requirements, including clustering (Wang et al., 2015b; Balcan et al., 2017), principal component analysis (Chaudhuri et al.”
- Differentially Private Algorithms for Learning Mixtures of Separated Gaussians (2019, methodology): “Within differential privacy, there are many algorithms for tasks that are related to learning mixtures of Gaussians, notably PCA [12, 49, 18, 33] and clustering [55, 39, 57, 56, 8, 62, 43].”
- Federated Kernelized Multi-Task Learning (2018, background): “…clustering in order to address the privacy concerns that inevitably come up Algorithm 1 Kernelized Federated Multi-Task Learning Update Ω centrally based on latest α (Section 3.2) 16: return: Ω , α when sharing users’ data [3], and which our current PBM-based solution does not take into account.”
- Locally Private k-Means in One Round (2021, methodology): “89 Furthermore, we point out that even experiments in the central model of Balcan et al. (2017), which uses almost the same data generation process (including separation parameters) as ours, suggest that the datasets are already challenging for the much more relaxed central DP model.”
- Federating Recommendations Using Differentially Private Prototypes (2020, methodology): “Unlike the approach of Balcan et al. (2017), this algorithm does not have guarantees on the convergence of the loss function.”