We consider three different variants of differential privacy (DP), namely approximate DP, R\'enyi DP (RDP), and hypothesis test DP. In the first part, we develop a machinery for optimally relating approximate DP to RDP based on the joint range of two $f$-divergences that underlie the approximate DP and RDP. In particular, this enables us to derive the optimal approximate DP parameters of a mechanism that satisfies a given level of RDP. As an application, we apply our result to the moments accountant framework for characterizing privacy guarantees of noisy stochastic gradient descent (SGD). When compared to the state-of-the-art, our bounds may lead to about 100 more stochastic gradient descent iterations for training deep learning models for the same privacy budget. In the second part, we establish a relationship between RDP and hypothesis test DP which allows us to translate the RDP constraint into a tradeoff between type I and type II error probabilities of a certain binary hypothesis test. We then demonstrate that for noisy SGD our result leads to tighter privacy guarantees compared to the recently proposed $f$-DP framework for some range of parameters.

In this paper we revisit the problem of private empirical risk minimziation (ERM) with differential privacy. We show that for unconstrained convex empirical risk minimization if the observed gradients of the objective function along the path of private gradient descent lie in a low-dimensional subspace (smaller than the ambient dimensionality of $p$), then using noisy adaptive preconditioning (a.k.a., noisy Adaptive Gradient Descent (AdaGrad)) we obtain a regret composed of two terms: a constant multiplicative factor of the original AdaGrad regret and an additional regret due to noise. In particular, we show that if the gradients lie in a constant rank subspace, then one can achieve an excess empirical risk of $ \tilde{O}(1/\epsilon n)$, compared to the worst-case achievable bound of $\tilde{O}(\sqrt{p}/\epsilon n)$. While previous works show dimension independent excess empirical risk bounds for the restrictive setting of convex generalized linear problems optimized over unconstrained subspaces, our results operate with general convex functions in unconstrained minimization. Along the way, we do a perturbation analysis of noisy AdaGrad, which may be of independent interest.

In a lot of real-world data mining and machine learning applications, data are provided by multiple providers and each maintains private records of different feature sets about common entities. It is challenging to train these vertically partitioned data effectively and efficiently while keeping data privacy for traditional data mining and machine learning algorithms. In this paper, we focus on nonlinear learning with kernels, and propose a federated doubly stochastic kernel learning (FDSKL) algorithm for vertically partitioned data. Specifically, we use random features to approximate the kernel mapping function and use doubly stochastic gradients to update the solutions, which are all computed federatedly without the disclosure of data. Importantly, we prove that FDSKL has a sublinear convergence rate, and can guarantee the data security under the semi-honest assumption. Extensive experimental results on a variety of benchmark datasets show that FDSKL is significantly faster than state-of-the-art federated learning methods when dealing with kernels, while retaining the similar generalization performance.

The goal of bayesian approach used in variational inference is to minimize the KL divergence between variational distribution and unknown posterior distribution. This is done by maximizing the Evidence Lower Bound (ELBO). A neural network is used to parametrize these distributions using Stochastic Gradient Descent. This work extends the work done by others by deriving the variational inference models. We show how SGD can be applied on bayesian neural networks by gradient estimation techniques. For validation, we have tested our model on 5 UCI datasets and the metrics chosen for evaluation are Root Mean Square Error (RMSE) error and negative log likelihood. Our work considerably beats the previous state of the art approaches for regression using bayesian neural networks.

Generative adversarial networks (GANs) have enjoyed tremendous empirical successes, and research interest in the theoretical understanding of GANs training process is rapidly growing, especially for its evolution and convergence analysis. This paper establishes approximations, with precise error bound analysis, for the training of GANs under stochastic gradient algorithms (SGAs). The approximations are in the form of coupled stochastic differential equations (SDEs). The analysis of the SDEs and the associated invariant measures yields conditions for the convergence of GANs training. Further analysis of the invariant measure for the coupled SDEs gives rise to a fluctuation-dissipation relations (FDRs) for GANs, revealing the trade-off of the loss landscape between the generator and the discriminator and providing guidance for learning rate scheduling.

This report considers the problem of Byzantine fault-tolerance in homogeneous multi-agent distributed learning. In this problem, each agent samples i.i.d. data points, and the goal for the agents is to compute a mathematical model that optimally fits, in expectation, the data points sampled by all the agents. We consider the case when a certain number of agents may be Byzantine faulty. Such faulty agents may not follow a prescribed learning algorithm. Faulty agents may share arbitrary incorrect information regarding their data points to prevent the non-faulty agents from learning a correct model. We propose a fault-tolerance mechanism for the distributed stochastic gradient descent (D-SGD) method -- a standard distributed supervised learning algorithm. Our fault-tolerance mechanism relies on a norm based gradient-filter, named comparative gradient elimination (CGE), that aims to mitigate the detrimental impact of malicious incorrect stochastic gradients shared by the faulty agents by limiting their Euclidean norms. We show that the CGE gradient-filter guarantees fault-tolerance against a bounded number of Byzantine faulty agents if the stochastic gradients computed by the non-faulty agents satisfy the standard assumption of bounded variance. We demonstrate the applicability of the CGE gradient-filer for distributed supervised learning of artificial neural networks. We show that the fault-tolerance by the CGE gradient-filter is comparable to that by other state-of-the-art gradient-filters, namely the multi-KRUM, geometric median of means, and coordinate-wise trimmed mean. Lastly, we propose a gradient averaging scheme that aims to reduce the sensitivity of a supervised learning process to individual agents' data batch-sizes. We show that gradient averaging improves the fault-tolerance property of a gradient-filter, including, but not limited to, the CGE gradient-filter.

In this paper, we study decentralized online stochastic non-convex optimization over a network of nodes. Integrating a technique called gradient tracking in decentralized stochastic gradient descent (DSGD), we show that the resulting algorithm, GT-DSGD, exhibits several important characteristics towards minimizing a sum of smooth non-convex functions. The main results of this paper can be divided into two categories: (1) For general smooth non-convex functions, we establish a non-asymptotic characterization of GT-DSGD and derive the conditions under which it achieves network-independent performance and matches centralized minibatch SGD. In comparison, the existing results suggest that the performance of GT-DSGD is always network-dependent and is therefore strictly worse than that of centralized minibatch SGD. (2) When the global function additionally satisfies the Polyak-Lojasiewics condition, we derive the exponential stability range for GT-DSGD under a constant step-size up to a steady-state error. Under stochastic approximation step-sizes, we establish, for the first time, the optimal global sublinear convergence rate on almost every sample path, in addition to the convergence rate in mean. Since strongly convex functions are a special case of this class of problems, our results are not only immediately applicable but also improve the currently known best convergence rates and their dependence on problem parameters.

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 privacy and adaptive data analysis to bound gradient estimation error at every iterate, which circumvents the worse generalization bound from the standard uniform convergence argument. Finally, we evaluate the proposed algorithms on two popular deep learning tasks and demonstrate the empirical advantages of DP adaptive gradient methods over standard DP SGD.

When I started my machine learning journey, math was something that always intrigued me and still does. I for one believe that libraries such as scikit learn have indeed done wonders for us when it comes to implementing the algorithms but without an understanding of the maths that goes into making the algorithm, we are bound to make mistakes on complicated problems. In this article, I will be going over the math behind Gradient Descent and the derivation behind the Normal linear Equation and then implementing them both on a dataset to get my coefficients. When i was getting started with Linear Regression and trying to get an understanding of the different ways to calculate the coefficients, The Normal Equation was by far my most favorite method to find coefficients but where does this equation come from? Well, let us take a look.

We give curvature-dependant convergence rates for the optimization of weakly convex functions defined on a manifold of 1-bounded geometry via Riemannian gradient descent and via the dynamic trivialization algorithm. In order to do this, we give a tighter bound on the norm of the Hessian of the Riemannian exponential than the previously known. We compute these bounds explicitly for some manifolds commonly used in the optimization literature such as the special orthogonal group and the real Grassmannian. Along the way, we present self-contained proofs of fully general bounds on the norm of the differential of the exponential map and certain cosine inequalities on manifolds, which are commonly used in optimization on manifolds.