Search Results for author:
Found 8 papers, 0 papers with code
Improved Communication-Privacy Trade-offs in $L_2$ Mean Estimation under Streaming Differential Privacy
We study $L_2$ mean estimation under central differential privacy and communication constraints, and address two key challenges: firstly, existing mean estimation schemes that simultaneously handle both constraints are usually optimized for $L_\infty$ geometry and rely on random rotation or Kashin's representation to adapt to $L_2$ geometry, resulting in suboptimal leading constants in mean square errors (MSEs); secondly, schemes achieving order-optimal communication-privacy trade-offs do not extend seamlessly to streaming differential privacy (DP) settings (e. g., tree aggregation or matrix factorization), rendering them incompatible with DP-FTRL type optimizers.
Training generative models from privatized data
Local differential privacy is a powerful method for privacy-preserving data collection.
The Poisson binomial mechanism for secure and private federated learning
Unlike previous discrete DP schemes based on additive noise, our mechanism encodes local information into a parameter of the binomial distribution, and hence the output distribution is discrete with bounded support.
The Fundamental Price of Secure Aggregation in Differentially Private Federated Learning
We consider the problem of training a $d$ dimensional model with distributed differential privacy (DP) where secure aggregation (SecAgg) is used to ensure that the server only sees the noisy sum of $n$ model updates in every training round.
Optimal Compression of Locally Differentially Private Mechanisms
Compressing the output of \epsilon-locally differentially private (LDP) randomizers naively leads to suboptimal utility.
Breaking The Dimension Dependence in Sparse Distribution Estimation under Communication Constraints
For the interactive setting, we propose a novel tree-based estimation scheme and show that the minimum sample-size needed to achieve dimension-free convergence can be further reduced to $n^*(s, d, b) = \tilde{O}\left( {s^2\log^2 d}/{2^b} \right)$.
Breaking the Communication-Privacy-Accuracy Trilemma
In particular, we consider the problems of mean estimation and frequency estimation under $\varepsilon$-local differential privacy and $b$-bit communication constraints.
Fisher information under local differential privacy
We develop data processing inequalities that describe how Fisher information from statistical samples can scale with the privacy parameter $\varepsilon$ under local differential privacy constraints.
