Robustness to distributional shift is one of the key challenges of contemporary machine learning. Attaining such robustness is the goal of distributionally robust optimization, which seeks a solution to an optimization problem that is worst-case robust under a specified distributional shift of an uncontrolled covariate. In this paper, we study such a problem when the distributional shift is measured via the maximum mean discrepancy (MMD). For the setting of zeroth-order, noisy optimization, we present a novel distributionally robust Bayesian optimization algorithm (DRBO). Our algorithm provably obtains sub-linear robust regret in various settings that differ in how the uncertain covariate is observed. We demonstrate the robust performance of our method on both synthetic and real-world benchmarks.

Generative adversarial networks (GANs) represent a zero-sum game between two machine players, a generator and a discriminator, designed to learn the distribution of data. While GANs have achieved state-of-the-art performance in several benchmark learning tasks, GAN minimax optimization still poses great theoretical and empirical challenges. GANs trained using first-order optimization methods commonly fail to converge to a stable solution where the players cannot improve their objective, i.e., the Nash equilibrium of the underlying game. Such issues raise the question of the existence of Nash equilibrium solutions in the GAN zero-sum game. In this work, we show through several theoretical and numerical results that indeed GAN zero-sum games may not have any local Nash equilibria. To characterize an equilibrium notion applicable to GANs, we consider the equilibrium of a new zero-sum game with an objective function given by a proximal operator applied to the original objective, a solution we call the proximal equilibrium. Unlike the Nash equilibrium, the proximal equilibrium captures the sequential nature of GANs, in which the generator moves first followed by the discriminator. We prove that the optimal generative model in Wasserstein GAN problems provides a proximal equilibrium. Inspired by these results, we propose a new approach, which we call proximal training, for solving GAN problems. We discuss several numerical experiments demonstrating the existence of proximal equilibrium solutions in GAN minimax problems.

An important problem that arises in reinforcement learning and Monte Carlo methods is estimating quantities defined by the stationary distribution of a Markov chain. In many real-world applications, access to the underlying transition operator is limited to a fixed set of data that has already been collected, without additional interaction with the environment being available. We show that consistent estimation remains possible in this challenging scenario, and that effective estimation can still be achieved in important applications. Our approach is based on estimating a ratio that corrects for the discrepancy between the stationary and empirical distributions, derived from fundamental properties of the stationary distribution, and exploiting constraint reformulations based on variational divergence minimization. The resulting algorithm, GenDICE, is straightforward and effective. We prove its consistency under general conditions, provide an error analysis, and demonstrate strong empirical performance on benchmark problems, including off-line PageRank and off-policy policy evaluation.

Deep networks have achieved remarkable performance in several application domains such as computer vision, natural language processing and genomics (Krizhevsky et al. 2012, Pennington et al. 2014, Duvenaud et al. 2015). A deep network can be framed as a chain of composition of modules, where each module is typically the composition of a nonlinear function and an affine transformation. The last module in the chain is usually task-specific and can be expressed either in analytical form as in supervised classification or as the solution of an optimization problem in dimension reduction or clustering. The optimization problem arising when training a deep network is often framed as a non-convex optimization problem, dismissing the structure of the objective yet central to the software implementation. Indeed optimization algorithms used to train deep networks proceed by making calls to first-order (or second-order) oracles relying on dynamic programming such as gradient back-propagation (Werbos 1994, Rumelhart et al. 1986, Lecun 1988).

Second-order gradient methods are among the most powerful algorithms in mathematical optimization. Algorithms in this family use a preconditioner matrix to transform the gradient before applying each step. Classically, this involves computing or approximating the matrix of second-order derivatives, i.e, the Hessian, in the context of exact deterministic optimization (e.g., Fletcher, 2013; Lewis & Overton, 2013; Nocedal, 1980). In contrast, AdaGrad (Duchi et al., 2011) and related algorithms that target stochastic optimization use the covariance matrix of second-order gradient statistics to form the preconditioner. While second-order methods often have significantly better convergence properties than first-order methods, the size of typical problems prohibits their use in practice, as they require quadratic storage and cubic computation time for each gradient update. Thus, these methods not commonly seen in the present practice of optimization in machine learning, which is largely dominated by the simpler to implement first-order methods. Arguably, one of the greatest challenges of modern optimization is to bridge this gap between the theoretical and practical optimization and make second-order optimization more feasible to implement and deploy. In this paper, we attempt to contribute towards narrowing this gap between theory and practice, focusing on second-order adaptive methods. These methods can be thought of as full-matrix analogues of common adaptive algorithms of the family of AdaGrad (Duchi et al., 2011) and Adam (Kingma & Ba, 2014).

In order to mitigate the high communication cost in distributed and federated learning, various vector compression schemes, such as quantization, sparsification and dithering, have become very popular. In designing a compression method, one aims to communicate as few bits as possible, which minimizes the cost per communication round, while at the same time attempting to impart as little distortion (variance) to the communicated messages as possible, which minimizes the adverse effect of the compression on the overall number of communication rounds. However, intuitively, these two goals are fundamentally in conflict: the more compression we allow, the more distorted the messages become. We formalize this intuition and prove an {\em uncertainty principle} for randomized compression operators, thus quantifying this limitation mathematically, and {\em effectively providing lower bounds on what might be achievable with communication compression}. Motivated by these developments, we call for the search for the optimal compression operator. In an attempt to take a first step in this direction, we construct a new unbiased compression method inspired by the Kashin representation of vectors, which we call {\em Kashin compression (KC)}. In contrast to all previously proposed compression mechanisms, we prove that KC enjoys a {\em dimension independent} variance bound with an explicit formula even in the regime when only a few bits need to be communicate per each vector entry. We show how KC can be provably and efficiently combined with several existing optimization algorithms, in all cases leading to communication complexity improvements on previous state of the art.

Setting regularization parameters for Lasso-type estimators is notoriously difficult, though crucial in practice. The most popular hyperparameter optimization approach is grid-search using held-out validation data. Grid-search however requires to choose a predefined grid for each parameter, which scales exponentially in the number of parameters. Another approach is to cast hyperparameter optimization as a bi-level optimization problem, one can solve by gradient descent. The key challenge for these methods is the estimation of the gradient with respect to the hyperparameters. Computing this gradient via forward or backward automatic differentiation is possible yet usually suffers from high memory consumption. Alternatively implicit differentiation typically involves solving a linear system which can be prohibitive and numerically unstable in high dimension. In addition, implicit differentiation usually assumes smooth loss functions, which is not the case for Lasso-type problems. This work introduces an efficient implicit differentiation algorithm, without matrix inversion, tailored for Lasso-type problems. Our approach scales to high-dimensional data by leveraging the sparsity of the solutions. Experiments demonstrate that the proposed method outperforms a large number of standard methods to optimize the error on held-out data, or the Stein Unbiased Risk Estimator (SURE).

An immensely powerful approach when X R n is to construct a second-order approximation to f(x) at the current iterate using first and second order information, denoted by ˆf(x), and move in the direction that minimizes this approximation, giving rise to a family of methods known as Newton methods (Kantorovich, 1948). A damped variant of the former applied to the minimization of a self-concordant function, converges globally, and shows quadratic local convergence when the iterates are close enough to the optimum (Nesterov & Nemirovskii, 1994). The global convergence of this method also extends to strongly convex and smooth function (Nesterov & Nemirovskii, 1994; Nesterov, 2013). Using a cubic regularized version of Newton's method, the global convergence of the method can also be extended to a broader class of functions than that of self-concordant or strongly convex and smooth functions (Nesterov & Polyak, 2006). When X R n is a convex set, one can use a constrained analog of these methods (Levitin & Polyak, 1966), where a quadratic approximation to the function is minimized over X at each iteration.

The sorting operation is one of the most basic and commonly used building blocks in computer programming. In machine learning, it is commonly used for robust statistics. However, seen as a function, it is piecewise linear and as a result includes many kinks at which it is non-differentiable. More problematic is the related ranking operator, commonly used for order statistics and ranking metrics. It is a piecewise constant function, meaning that its derivatives are null or undefined. While numerous works have proposed differentiable proxies to sorting and ranking, they do not achieve the $O(n \log n)$ time complexity one would expect from sorting and ranking operations. In this paper, we propose the first differentiable sorting and ranking operators with $O(n \log n)$ time and $O(n)$ space complexity. Our proposal in addition enjoys exact computation and differentiation. We achieve this feat by constructing differentiable sorting and ranking operators as projections onto the permutahedron, the convex hull of permutations, and using a reduction to isotonic optimization. Empirically, we confirm that our approach is an order of magnitude faster than existing approaches and showcase two novel applications: differentiable Spearman's rank correlation coefficient and soft least trimmed squares.

Optimal transport is a foundational problem in optimization, that allows to compare probability distributions while taking into account geometric aspects. Its optimal objective value, the Wasserstein distance, provides an important loss between distributions that has been used in many applications throughout machine learning and statistics. Recent algorithmic progress on this problem and its regularized versions have made these tools increasingly popular. However, existing techniques require solving an optimization problem to obtain a single gradient of the loss, thus slowing down first-order methods to minimize the sum of losses, that require many such gradient computations. In this work, we introduce an algorithm to solve a regularized version of this problem of Wasserstein estimators, with a time per step which is sublinear in the natural dimensions of the problem. We introduce a dual formulation, and optimize it with stochastic gradient steps that can be computed directly from samples, without solving additional optimization problems at each step. Doing so, the estimation and computation tasks are performed jointly. We show that this algorithm can be extended to other tasks, including estimation of Wasserstein barycenters. We provide theoretical guarantees and illustrate the performance of our algorithm with experiments on synthetic data.