Search Results for author:
Found 9 papers, 1 papers with code
Differentially Private Decentralized Learning with Random Walks
The popularity of federated learning comes from the possibility of better scalability and the ability for participants to keep control of their data, improving data security and sovereignty.
A Unifying Framework for Differentially Private Sums under Continual Observation
We give a constructive proof for an almost exact upper bound on the $\gamma_2$ and $\gamma_F$ norm and an almost tight lower bound on the $\gamma_2$ norm for a large class of lower-triangular matrices.
Almost Tight Error Bounds on Differentially Private Continual Counting
Our lower bound for any continual counting mechanism is the first tight lower bound on continual counting under approximate differential privacy.
Differentially Private Sampling from Rashomon Sets, and the Universality of Langevin Diffusion for Convex Optimization
In this paper we provide an algorithmic framework based on Langevin diffusion (LD) and its corresponding discretizations that allow us to simultaneously obtain: i) An algorithm for sampling from the exponential mechanism, whose privacy analysis does not depend on convexity and which can be stopped at anytime without compromising privacy, and ii) tight uniform stability guarantees for the exponential mechanism.
Constant matters: Fine-grained Complexity of Differentially Private Continual Observation
Finally, we note that our result can be used to get a fine-grained error bound for non-interactive local learning {and the first lower bounds on the additive error for $(\epsilon,\delta)$-differentially-private counting under continual observation.}
A Framework for Private Matrix Analysis
We give first efficient $o(W)$ space differentially private algorithms for spectral approximation, principal component analysis, and linear regression.
On Differentially Private Graph Sparsification and Applications
In this paper, we study private sparsification of graphs.
Differentially Private Robust Low-Rank Approximation
In this paper, we study the following robust low-rank matrix approximation problem: given a matrix $A \in \R^{n \times d}$, find a rank-$k$ matrix $B$, while satisfying differential privacy, such that $ \norm{ A - B }_p \leq \alpha \mathsf{OPT}_k(A) + \tau,$ where $\norm{ M }_p$ is the entry-wise $\ell_p$-norm and $\mathsf{OPT}_k(A):=\min_{\mathsf{rank}(X) \leq k} \norm{ A - X}_p$.
The Price of Privacy for Low-rank Factorization
Even though these settings are well studied without privacy, surprisingly, there are no private algorithm for these settings (except when a matrix is updated row by row).
