Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation
Paul G Allen School of Computer Science and Engineering, University of Washington（华盛顿大学保罗·G·艾伦计算机科学与工程学院）；Boston University（波士顿大学）；Google DeepMind（谷歌DeepMind）
我们对平方误差损失下线性回归的标准差分隐私梯度下降进行了改进分析。在对输入的适度假设下，我们刻画了每个时间步迭代点的分布。我们的分析带来了关于算法精度的新结果：在适当固定的超参数选择下，样本复杂度仅线性依赖于数据维度。这与（非私有的）普通最小二乘估计器以及近期依赖复杂自适应梯度裁剪方案的私有算法的维度依赖性相匹配（Varshney et al., 2022；Liu et al., 2023）。我们对迭代点分布的分析还使我们能够为经验优化器构造置信区间，这些置信区间会自动适应算法在特定数据集上的方差。我们通过在合成数据上的实验验证了我们的定理。
英文摘要：
We provide an improved analysis of standard differentially private gradient descent for linear regression under the squared error loss. Under modest assumptions on the input, we characterize the distribution of the iterate at each time step.
Our analysis leads to new results on the algorithm's accuracy: for a proper fixed choice of hyperparameters, the sample complexity depends only linearly on the dimension of the data. This matches the dimension-dependence of the (non-private) ordinary least squares estimator as well as that of recent private algorithms that rely on sophisticated adaptive gradient-clipping schemes (Varshney et al., 2022; Liu et al., 2023).
Our analysis of the iterates' distribution also allows us to construct confidence intervals for the empirical optimizer which adapt automatically to the variance of the algorithm on a particular data set. We validate our theorems through experiments on synthetic data.
We study the problem of differentially private (DP) matrix completion under user-level privacy. We design a joint differentially private variant of the popular Alternating-Least-Squares (ALS) method that achieves: i) (nearly) optimal sample complexity for matrix completion (in terms of number of items, users), and ii) the best known privacy/utility trade-off both theoretically, as well as on benchmark data sets. In particular, we provide the first global convergence analysis of ALS with noise introduced to ensure DP, and show that, in comparison to the best known alternative (the Private Frank…
We study differentially private (DP) algorithms for stochastic non-convex optimization. In this problem, the goal is to minimize the population loss over a $p$-dimensional space given $n$ i.i.d. samples drawn from a distribution. We improve upon the population gradient bound of ${\sqrt{p}}/{\sqrt{n}}$ from prior work and obtain a sharper rate of $\sqrt[4]{p}/\sqrt{n}$. We obtain this rate by providing the first analyses on a collection of private gradient-based methods, including adaptive algorithms DP RMSProp and DP Adam. Our proof technique leverages the connection between differential priva…
We consider the problem of empirical risk minimization given a database, using the gradient descent algorithm. We note that the function to be optimized may be non-convex, consisting of saddle points which impede the convergence of the algorithm. A perturbed gradient descent algorithm is typically employed to escape these saddle points. We show that this algorithm, that perturbs the gradient, inherently preserves the privacy of the data. We then employ the differential privacy framework to quantify the privacy hence achieved. We also analyze the change in privacy with varying parameters such a…
Private machine learning involves addition of noise while training, resulting in lower accuracy. Intuitively, greater stability can imply greater privacy and improve this privacy-utility tradeoff. We study this role of stability in private empirical risk minimization, where differential privacy is achieved by output perturbation, and establish a corresponding theoretical result showing that for strongly-convex loss functions, an algorithm with uniform stability of $β$ implies a bound of $O(\sqrtβ)$ on the scale of noise required for differential privacy. The result applies to both explicit reg…
Federated learning enables multiple, distributed participants (potentially on different clouds) to collaborate and train machine/deep learning models by sharing parameters/gradients. However, sharing gradients, instead of centralizing data, may not be as private as one would expect. Reverse engineering attacks on plaintext gradients have been demonstrated to be practically feasible. Existing solutions for differentially private federated learning, while promising, lead to less accurate models and require nontrivial hyperparameter tuning. In this paper, we examine the use of additive homomorphi…
When we enforce differential privacy in machine learning, the utility-privacy trade-off is different w.r.t. each group. Gradient clipping and random noise addition disproportionately affect underrepresented and complex classes and subgroups, which results in inequality in utility loss. In this work, we analyze the inequality in utility loss by differential privacy and propose a modified differentially private stochastic gradient descent (DPSGD), called DPSGD-F, to remove the potential disparate impact of differential privacy on the protected group. DPSGD-F adjusts the contribution of samples i…
We revisit the well-studied problem of differentially private empirical risk minimization (ERM). We show that for unconstrained convex generalized linear models (GLMs), one can obtain an excess empirical risk of $\tilde O\left(\sqrt{\texttt{rank}}/εn\right)$, where ${\texttt{rank}}$ is the rank of the feature matrix in the GLM problem, $n$ is the number of data samples, and $ε$ is the privacy parameter. This bound is attained via differentially private gradient descent (DP-GD). Furthermore, via the first lower bound for unconstrained private ERM, we show that our upper bound is tight. In sharp…
Michigan State University（密歇根州立大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）
Protecting privacy in learning while maintaining the model performance has become increasingly critical in many applications that involve sensitive data. Private Gradient Descent (PGD) is a commonly used private learning framework, which noises gradients based on the Differential Privacy protocol. Recent studies show that \emph{dynamic privacy schedules} of decreasing noise magnitudes can improve loss at the final iteration, and yet theoretical understandings of the effectiveness of such schedules and their connections to optimization algorithms remain limited. In this paper, we provide compre…
University of Georgia（佐治亚大学）；Penn State University（宾夕法尼亚州立大学）
Iterative algorithms, like gradient descent, are common tools for solving a variety of problems, such as model fitting. For this reason, there is interest in creating differentially private versions of them. However, their conversion to differentially private algorithms is often naive. For instance, a fixed number of iterations are chosen, the privacy budget is split evenly among them, and at each iteration, parameters are updated with a noisy gradient. In this paper, we show that gradient-based algorithms can be improved by a more careful allocation of privacy budget per iteration. Intuitivel…
Electronic Information School, Wuhan University（武汉大学）；Department of Electrical and Computer Engineering, North Carolina State University（北卡罗来纳州立大学）
While machine learning has achieved remarkable results in a wide variety of domains, the training of models often requires large datasets that may need to be collected from different individuals. As sensitive information may be contained in the individual's dataset, sharing training data may lead to severe privacy concerns. Therefore, there is a compelling need to develop privacy-aware machine learning methods, for which one effective approach is to leverage the generic framework of differential privacy. Considering that stochastic gradient descent (SGD) is one of the most commonly adopted met…
Statistical Inference for Differentially Private Stochastic Gradient Descent
Center for Data Science, Zhejiang University（浙江大学数据科学中心）；Department of Statistics, Rutgers University（罗格斯大学统计系）；Faculty of Business and Economics, The University of Hong Kong（香港大学商学院）
University of California, San Diego（加利福尼亚大学圣地亚哥分校）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Google（谷歌）
While significant progress has been made separately on analytics systems for scalable stochastic gradient descent (SGD) and private SGD, none of the major scalable analytics frameworks have incorporated differentially private SGD. There are two inter-related issues for this disconnect between research and practice: (1) low model accuracy due to added noise to guarantee privacy, and (2) high development and runtime overhead of the private algorithms. This paper takes a first step to remedy this disconnect and proposes a private SGD algorithm to address \emph{both} issues in an integrated manner…
In this paper, we consider efficient differentially private empirical risk minimization from the viewpoint of optimization algorithms. For strongly convex and smooth objectives, we prove that gradient descent with output perturbation not only achieves nearly optimal utility, but also significantly improves the running time of previous state-of-the-art private optimization algorithms, for both $ε$-DP and $(ε, δ)$-DP. For non-convex but smooth objectives, we propose an RRPSGD (Random Round Private Stochastic Gradient Descent) algorithm, which provably converges to a stationary point with privacy…
University of Washington（华盛顿大学）；Google Research（谷歌研究院）
We study the canonical statistical estimation problem of linear regression from $n$ i.i.d.~examples under $(\varepsilon,δ)$-differential privacy when some response variables are adversarially corrupted. We propose a variant of the popular differentially private stochastic gradient descent (DP-SGD) algorithm with two innovations: a full-batch gradient descent to improve sample complexity and a novel adaptive clipping to guarantee robustness. When there is no adversarial corruption, this algorithm improves upon the existing state-of-the-art approach and achieves a near optimal sample complexity.…
We propose a new framework of synthesizing data using deep generative models in a differentially private manner. Within our framework, sensitive data are sanitized with rigorous privacy guarantees in a one-shot fashion, such that training deep generative models is possible without re-using the original data. Hence, no extra privacy costs or model constraints are incurred, in contrast to popular approaches such as Differentially Private Stochastic Gradient Descent (DP-SGD), which, among other issues, causes degradation in privacy guarantees as the training iteration increases. We demonstrate a …
We revisit the problem of differentially private release of classification queries. In this problem, the goal is to design an algorithm that can accurately answer a sequence of classification queries based on a private training set while ensuring differential privacy. We formally study this problem in the agnostic PAC model and derive a new upper bound on the private sample complexity. Our results improve over those obtained in a recent work [BTT18] for the agnostic PAC setting. In particular, we give an improved construction that yields a tighter upper bound on the sample complexity. Moreover…
In shuffle privacy, each user sends a collection of randomized messages to a trusted shuffler, the shuffler randomly permutes these messages, and the resulting shuffled collection of messages must satisfy differential privacy. Prior work in this model has largely focused on protocols that use a single round of communication to compute algorithmic primitives like means, histograms, and counts. We present interactive shuffle protocols for stochastic convex optimization. Our protocols rely on a new noninteractive protocol for summing vectors of bounded $\ell_2$ norm. By combining this sum subrout…
Privacy-preserving deep learning is crucial for deploying deep neural network based solutions, especially when the model works on data that contains sensitive information. Most privacy-preserving methods lead to undesirable performance degradation. Ensemble learning is an effective way to improve model performance. In this work, we propose a new method for teacher ensembles that uses more informative network outputs under differential private stochastic gradient descent and provide provable privacy guarantees. Out method employs knowledge distillation and hint learning on intermediate represen…
We consider a decentralized learning setting in which data is distributed over nodes in a graph. The goal is to learn a global model on the distributed data without involving any central entity that needs to be trusted. While gossip-based stochastic gradient descent (SGD) can be used to achieve this learning objective, it incurs high communication and computation costs, since it has to wait for all the local models at all the nodes to converge. To speed up the convergence, we propose instead to study random walk based SGD in which a global model is updated based on a random walk on the graph. …
Applying Differentially Private Stochastic Gradient Descent (DPSGD) to training modern, large-scale neural networks such as transformer-based models is a challenging task, as the magnitude of noise added to the gradients at each iteration scales with model dimension, hindering the learning capability significantly. We propose a unified framework, $\textsf{LSG}$, that fully exploits the low-rank and sparse structure of neural networks to reduce the dimension of gradient updates, and hence alleviate the negative impacts of DPSGD. The gradient updates are first approximated with a pair of low-ran…
Privacy preserving machine learning algorithms are crucial for learning models over user data to protect sensitive information. Motivated by this, differentially private stochastic gradient descent (SGD) algorithms for training machine learning models have been proposed. At each step, these algorithms modify the gradients and add noise proportional to the sensitivity of the modified gradients. Under this framework, we propose AdaCliP, a theoretically motivated differentially private SGD algorithm that provably adds less noise compared to the previous methods, by using coordinate-wise adaptive …
In this paper, we revisit the problem of private stochastic convex optimization. We propose an algorithm based on noisy mirror descent, which achieves optimal rates both in terms of statistical complexity and number of queries to a first-order stochastic oracle in the regime when the privacy parameter is inversely proportional to the number of samples.
Understanding Private Learning From Feature Perspective
Department of Computer Science and Engineering, State University of New York at Buffalo（纽约州立大学布法罗分校计算机科学与工程系）；Division of CEMSE, King Abdullah University of Science and Technology（卡普兰大学科学与技术大学CEMSE分校）；Institute of Artificial Intelligence and Blockchain, Guangzhou University（广州大学人工智能与区块链研究院）；School of Information Science and Technology, University of Science and Technology of China（中国科学技术大学信息科学与技术学院）
We develop theoretically guaranteed stochastic methods for outlier-robust PCA. Outlier-robust PCA seeks an underlying low-dimensional linear subspace from a dataset that is corrupted with outliers. We are able to show that our methods, which involve stochastic geodesic gradient descent over the Grassmannian manifold, converge and recover an underlying subspace in various regimes through the development of a novel convergence analysis. The main application of this method is an effective differentially private algorithm for outlier-robust PCA that uses a Gaussian noise mechanism within the stoch…
Tight Generalization Error Bounds for Stochastic Gradient Descent in Non-convex Learning
School of Mathematics and Statistics（数学与统计学学院）；Guangxi Normal University（广西师范大学）；School of Mathematics（数学学院）；Hohai University（河海大学）；College of Marine Life Sciences（海洋生命科学学院）；Ocean University of China（中国海洋大学）；State Key Laboratory of Mathematical Sciences（数学科学国家重点实验室）；Academy of Mathematics and Systems Science（数学与系统科学研究院）；University of Chinese Academy of Sciences（中国科学院大学）
Online Convex Optimization plays a key role in large scale machine learning. Early approaches to this problem were conservative, in which the main focus was protection against the worst case scenario. But recently several algorithms have been developed for tightening the regret bounds in easy data instances such as sparsity, predictable sequences, and curved losses. In this work we unify some of these existing techniques to obtain new update rules for the cases when these easy instances occur together. First we analyse an adaptive and optimistic update rule which achieves tighter regret bound …
Northeastern University（东北大学）；IBM Research – Almaden（IBM阿尔马登研究院）；Google Research, Brain Team（谷歌研究院大脑团队）
Private data analysis suffers a costly curse of dimensionality. However, the data often has an underlying low-dimensional structure. For example, when optimizing via gradient descent, the gradients often lie in or near a low-dimensional subspace. If that low-dimensional structure can be identified, then we can avoid paying (in terms of privacy or accuracy) for the high ambient dimension. We present differentially private algorithms that take input data sampled from a low-dimensional linear subspace (possibly with a small amount of error) and output that subspace (or an approximation to it). Th…
We introduce new algorithms and convergence guarantees for privacy-preserving non-convex Empirical Risk Minimization (ERM) on smooth $d$-dimensional objectives. We develop an improved sensitivity analysis of stochastic gradient descent on smooth objectives that exploits the recurrence of examples in different epochs. By combining this new approach with recent analysis of momentum with private aggregation techniques, we provide an $(ε,δ)$-differential private algorithm that finds a gradient of norm $\tilde O\left(\frac{d^{1/3}}{(εN)^{2/3}}\right)$ in $O\left(\frac{N^{7/3}ε^{4/3}}{d^{2/3}}\right…
What is the information leakage of an iterative randomized learning algorithm about its training data, when the internal state of the algorithm is \emph{private}? How much is the contribution of each specific training epoch to the information leakage through the released model? We study this problem for noisy gradient descent algorithms, and model the \emph{dynamics} of Rényi differential privacy loss throughout the training process. Our analysis traces a provably \emph{tight} bound on the Rényi divergence between the pair of probability distributions over parameters of models trained on neigh…
Rensselaer Polytechnic Institute（伦斯勒理工学院）；University of California, Los Angeles（加州大学洛杉矶分校）
Stochastic nested optimization, including stochastic compositional, min-max and bilevel optimization, is gaining popularity in many machine learning applications. While the three problems share the nested structure, existing works often treat them separately, and thus develop problem-specific algorithms and their analyses. Among various exciting developments, simple SGD-type updates (potentially on multiple variables) are still prevalent in solving this class of nested problems, but they are believed to have slower convergence rate compared to that of the non-nested problems. This paper unifie…
Stanford University（斯坦福大学）；Apple（苹果公司）；Massachusetts Institute of Technology（麻省理工学院）
We study adaptive methods for differentially private convex optimization, proposing and analyzing differentially private variants of a Stochastic Gradient Descent (SGD) algorithm with adaptive stepsizes, as well as the AdaGrad algorithm. We provide upper bounds on the regret of both algorithms and show that the bounds are (worst-case) optimal. As a consequence of our development, we show that our private versions of AdaGrad outperform adaptive SGD, which in turn outperforms traditional SGD in scenarios with non-isotropic gradients where (non-private) Adagrad provably outperforms SGD. The major…
Apple（苹果公司）；University of California, Berkeley（加利福尼亚大学伯克利分校）
We consider a sequential setting in which a single dataset of individuals is used to perform adaptively-chosen analyses, while ensuring that the differential privacy loss of each participant does not exceed a pre-specified privacy budget. The standard approach to this problem relies on bounding a worst-case estimate of the privacy loss over all individuals and all possible values of their data, for every single analysis. Yet, in many scenarios this approach is overly conservative, especially for "typical" data points which incur little privacy loss by participation in most of the analyses. In …
We revisit on-average algorithmic stability of GD for training overparameterised shallow neural networks and prove new generalisation and excess risk bounds without the NTK or PL assumptions. In particular, we show oracle type bounds which reveal that the generalisation and excess risk of GD is controlled by an interpolating network with the shortest GD path from initialisation (in a sense, an interpolating network with the smallest relative norm). While this was known for kernelised interpolants, our proof applies directly to networks trained by GD without intermediate kernelisation. At the s…
