Gaussian Differential Privacy google
Differential privacy has seen remarkable success as a rigorous and practical formalization of data privacy in the past decade. But it also has some well known weaknesses: notably, it does not tightly handle composition. This weakness has inspired several recent relaxations of differential privacy based on Renyi divergences. We propose an alternative relaxation of differential privacy, which we term ‘$f$-differential privacy’, which has a number of appealing properties and avoids some of the difficulties associated with divergence based relaxations. First, it preserves the hypothesis testing interpretation of differential privacy, which makes its guarantees easily interpretable. It allows for lossless reasoning about composition and post-processing, and notably, a direct way to import existing tools from differential privacy, including privacy amplification by subsampling. We define a canonical single parameter family of definitions within our class which we call ‘Gaussian Differential Privacy’, defined based on the hypothesis testing of two shifted Gaussian distributions. We show that this family is focal by proving a central limit theorem, which shows that the privacy guarantees of \emph{any} hypothesis-testing based definition of privacy (including differential privacy) converges to Gaussian differential privacy in the limit under composition. We also prove a finite (Berry-Esseen style) version of the central limit theorem, which gives a useful tool for tractably analyzing the exact composition of potentially complicated expressions. We demonstrate the use of the tools we develop by giving an improved analysis of the privacy guarantees of noisy stochastic gradient descent. …

Benford’s Law google
Benford’s Law, also called the First-Digit Law, refers to the frequency distribution of digits in many (but not all) real-life sources of data. In this distribution, the number 1 occurs as the leading digit about 30% of the time, while larger numbers occur in that position less frequently: 9 as the first digit less than 5% of the time. Benford’s Law also concerns the expected distribution for digits beyond the first, which approach a uniform distribution. …

Soft-Robust Actor-Critic algorithm (SR-AC) google
Robust Reinforcement Learning aims to derive an optimal behavior that accounts for model uncertainty in dynamical systems. However, previous studies have shown that by considering the worst case scenario, robust policies can be overly conservative. Our \textit{soft-robust} framework is an attempt to overcome this issue. In this paper, we present a novel Soft-Robust Actor-Critic algorithm (SR-AC). It learns an optimal policy with respect to a distribution over an uncertainty set and stays robust to model uncertainty but avoids the conservativeness of robust strategies. We show convergence of the SR-AC and test the efficiency of our approach on different domains by comparing it against regular learning methods and their robust formulations. …

LS-Tree google
We study the problem of interpreting trained classification models in the setting of linguistic data sets. Leveraging a parse tree, we propose to assign least-squares based importance scores to each word of an instance by exploiting syntactic constituency structure. We establish an axiomatic characterization of these importance scores by relating them to the Banzhaf value in coalitional game theory. Based on these importance scores, we develop a principled method for detecting and quantifying interactions between words in a sentence. We demonstrate that the proposed method can aid in interpretability and diagnostics for several widely-used language models. …

Advertisements