ترغب بنشر مسار تعليمي؟ اضغط هنا

Fast and Memory Efficient Differentially Private-SGD via JL Projections

104   0   0.0 ( 0 )
 نشر من قبل Sivakanth Gopi
 تاريخ النشر 2021
  مجال البحث الهندسة المعلوماتية
والبحث باللغة English




اسأل ChatGPT حول البحث

Differentially Private-SGD (DP-SGD) of Abadi et al. (2016) and its variations are the only known algorithms for private training of large scale neural networks. This algorithm requires computation of per-sample gradients norms which is extremely slow and memory intensive in practice. In this paper, we present a new framework to design differentially private optimizers called DP-SGD-JL and DP-Adam-JL. Our approach uses Johnson-Lindenstrauss (JL) projections to quickly approximate the per-sample gradient norms without exactly computing them, thus making the training time and memory requirements of our optimizers closer to that of their non-



قيم البحث

اقرأ أيضاً

Common datasets have the form of elements with keys (e.g., transactions and products) and the goal is to perform analytics on the aggregated form of key and frequency pairs. A weighted sample of keys by (a function of) frequency is a highly versatile summary that provides a sparse set of representative keys and supports approximate evaluations of query statistics. We propose private weighted sampling (PWS): A method that ensures element-level differential privacy while retaining, to the extent possible, the utility of a respective non-private weighted sample. PWS maximizes the reporting probabilities of keys and estimation quality of a broad family of statistics. PWS improves over the state of the art also for the well-studied special case of private histograms, when no sampling is performed. We empirically demonstrate significant performance gains compared with prior baselines: 20%-300% increase in key reporting for common Zipfian frequency distributions and accuracy for $times 2$-$ 8$ lower frequencies in estimation tasks. Moreover, PWS is applied as a simple post-processing of a non-private sample, without requiring the original data. This allows for seamless integration with existing implementations of non-private schemes and retaining the efficiency of schemes designed for resource-constrained settings such as massive distributed or streamed data. We believe that due to practicality and performance, PWS may become a method of choice in applications where privacy is desired.
Correlation clustering is a widely used technique in unsupervised machine learning. Motivated by applications where individual privacy is a concern, we initiate the study of differentially private correlation clustering. We propose an algorithm that achieves subquadratic additive error compared to the optimal cost. In contrast, straightforward adaptations of existing non-private algorithms all lead to a trivial quadratic error. Finally, we give a lower bound showing that any pure differentially private algorithm for correlation clustering requires additive error of $Omega(n)$.
Differential privacy has emerged as a standard requirement in a variety of applications ranging from the U.S. Census to data collected in commercial devices, initiating an extensive line of research in accurately and privately releasing statistics of a database. An increasing number of such databases consist of data from multiple sources, not all of which can be trusted. This leaves existing private analyses vulnerable to attacks by an adversary who injects corrupted data. Despite the significance of designing algorithms that guarantee privacy and robustness (to a fraction of data being corrupted) simultaneously, even the simplest questions remain open. For the canonical problem of estimating the mean from i.i.d. samples, we introduce the first efficient algorithm that achieves both privacy and robustness for a wide range of distributions. This achieves optimal accuracy matching the known lower bounds for robustness, but the sample complexity has a factor of $d^{1/2}$ gap from known lower bounds. We further show that this gap is due to the computational efficiency; we introduce the first family of algorithms that close this gap but takes exponential time. The innovation is in exploiting resilience (a key property in robust estimation) to adaptively bound the sensitivity and improve privacy.
Federated learning (FL) is a distributed learning paradigm in which many clients with heterogeneous, unbalanced, and often sensitive local data, collaborate to learn a model. Local Differential Privacy (LDP) provides a strong guarantee that each clie nts data cannot be leaked during and after training, without relying on a trusted third party. While LDP is often believed to be too stringent to allow for satisfactory utility, our paper challenges this belief. We consider a general setup with unbalanced, heterogeneous data, disparate privacy needs across clients, and unreliable communication, where a random number/subset of clients is available each round. We propose three LDP algorithms for smooth (strongly) convex FL; each are noisy variations of distributed minibatch SGD. One is accelerated and one involves novel time-varying noise, which we use to obtain the first non-trivial LDP excess risk bound for the fully general non-i.i.d. FL problem. Specializing to i.i.d. clients, our risk bounds interpolate between the best known and/or optimal bounds in the centralized setting and the cross-device setting, where each client represents just one persons data. Furthermore, we show that in certain regimes, our convergence rate (nearly) matches the corresponding non-private lower bound or outperforms state of the art non-private algorithms (``privacy for free). Finally, we validate our theoretical results and illustrate the practical utility of our algorithm with numerical experiments.
In this work we consider the problem of online submodular maximization under a cardinality constraint with differential privacy (DP). A stream of $T$ submodular functions over a common finite ground set $U$ arrives online, and at each time-step the d ecision maker must choose at most $k$ elements of $U$ before observing the function. The decision maker obtains a payoff equal to the function evaluated on the chosen set, and aims to learn a sequence of sets that achieves low expected regret. In the full-information setting, we develop an $(varepsilon,delta)$-DP algorithm with expected $(1-1/e)$-regret bound of $mathcal{O}left( frac{k^2log |U|sqrt{T log k/delta}}{varepsilon} right)$. This algorithm contains $k$ ordered experts that learn the best marginal increments for each item over the whole time horizon while maintaining privacy of the functions. In the bandit setting, we provide an $(varepsilon,delta+ O(e^{-T^{1/3}}))$-DP algorithm with expected $(1-1/e)$-regret bound of $mathcal{O}left( frac{sqrt{log k/delta}}{varepsilon} (k (|U| log |U|)^{1/3})^2 T^{2/3} right)$. Our algorithms contains $k$ ordered experts that learn the best marginal item to select given the items chosen her predecessors, while maintaining privacy of the functions. One challenge for privacy in this setting is that the payoff and feedback of expert $i$ depends on the actions taken by her $i-1$ predecessors. This particular type of information leakage is not covered by post-processing, and new analysis is required. Our techniques for maintaining privacy with feedforward may be of independent interest.

الأسئلة المقترحة

التعليقات
جاري جلب التعليقات جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا