24 citations · 64 across the 23 of their papers we have counts for
4 papers · 1 filter
Shape And Structure Preserving Differential Privacy
Carlos Soto, Karthik Bharath, Matthew Reimherr +1
It is common for data structures such as images and shapes of 2D objects to be represented as points on a manifold. The utility of a mechanism to produce sanitized differentially p…
On Hypothesis Transfer Learning of Functional Linear Models
Haotian Lin, Matthew Reimherr
We study the transfer learning (TL) for the functional linear regression (FLR) under the Reproducing Kernel Hilbert Space (RKHS) framework, observing that the TL techniques in exis…
Exact Privacy Guarantees for Markov Chain Implementations of the Exponential Mechanism with Artificial Atoms
Jeremy Seeman, Matthew Reimherr, Aleksandra Slavkovic
Implementations of the exponential mechanism in differential privacy often require sampling from intractable distributions. When approximate procedures like Markov chain Monte Carl…
Formal Privacy for Partially Private Data
Jeremy Seeman, Matthew Reimherr, Aleksandra Slavkovic
Differential privacy (DP) quantifies privacy loss by analyzing noise injected into output statistics. For non-trivial statistics, this noise is necessary to ensure finite privacy l…