In recent years, low-rank tensor completion (LRTC) has received considerable attention due to its applications in image/video inpainting, hyperspectral data recovery, etc. With different notions of tensor rank (e.g., CP, Tucker, tensor train/ring, etc.), various optimization based numerical methods are proposed to LRTC. However, tensor network based methods have not been proposed yet. In this paper, we propose to solve LRTC via tensor networks with a Tucker wrapper. Here by "Tucker wrapper" we mean that the outermost factor matrices of the tensor network are all orthonormal. We formulate LRTC as a problem of solving a system of nonlinear equations, rather than a constrained optimization problem. A two-level alternative least square method is then employed to update the unknown factors. The computation of the method is dominated by tensor matrix multiplications and can be efficiently performed. Also, under proper assumptions, it is shown that with high probability, the method converges to the exact solution at a linear rate. Numerical simulations show that the proposed algorithm is comparable with state-of-the-art methods.

Off-policy evaluation provides an essential tool for evaluating the effects of different policies or treatments using only observed data. When applied to high-stakes scenarios such as medical diagnosis or financial decision-making, it is crucial to provide provably correct upper and lower bounds of the expected reward, not just a classical single point estimate, to the end-users, as executing a poor policy can be very costly. In this work, we propose a provably correct method for obtaining interval bounds for off-policy evaluation in a general continuous setting. The idea is to search for the maximum and minimum values of the expected reward among all the Lipschitz Q-functions that are consistent with the observations, which amounts to solving a constrained optimization problem on a Lipschitz function space. We go on to introduce a Lipschitz value iteration method to monotonically tighten the interval, which is simple yet efficient and provably convergent. We demonstrate the practical efficiency of our method on a range of benchmarks.

Machine learning often reduces to estimating some model parameters. This approach raises at least two orders of questions: first, multiple solutions may exist, amongst which a specific one must be selected; second, potential instabilities with respect to noise and sampling must be controlled. A classical way to achieve both goals is to consider explicitly penalized or constrained objective functions. In machine learning, this leads to regularized empirical risk minimization (Shalev-Shwartz and Ben-David, 2014). A more recent approach is based on directly exploiting an iterative optimization procedure for an unconstrained/unpenalized problem. This approach is shared by several related ideas. One is implicit regularization (Mahoney, 2012; Gunasekar et al., 2017), stemming from the observation that the bias is controlled increasing the number of iterations, just like in penalized methods it is controlled decreasing the penalty parameter. Another one is early stopping (Yao et al., 2007; Raskutti et al., 2014), putting emphasis on the fact that running the iterates to convergence might lead to instabilities in the presence of noise. Yet another, and more classical, idea is iterative regularization, where both aspects (convergence and stability) are considered to be relevant (Engl et al., 1996; Kaltenbacher et al., 2008).

Automatic differentiation, as implemented today, does not have a simple mathematical model adapted to the needs of modern machine learning. In this work we articulate the relationships between differentiation of programs as implemented in practice and differentiation of nonsmooth functions. To this end we provide a simple class of functions, a nonsmooth calculus, and show how they apply to stochastic approximation methods. We also evidence the issue of artificial critical points created by algorithmic differentiation and show how usual methods avoid these points with probability one.

In machine learning, data is usually represented in a (flat) Euclidean space where distances between points are along straight lines. Researchers have recently considered more exotic (non-Euclidean) Riemannian manifolds such as hyperbolic space which is well suited for tree-like data. In this paper, we propose a representation living on a pseudo-Riemannian manifold of constant nonzero curvature. It is a generalization of hyperbolic and spherical geometries where the non-degenerate metric tensor need not be positive definite. We provide the necessary learning tools in this geometry and extend gradient method optimization techniques. More specifically, we provide closed-form expressions for distances via geodesics and define a descent direction to minimize some objective function. Our novel framework is applied to graph representations.

We propose a graph spectrum-based Gaussian process for prediction of signals defined on nodes of the graph. The model is designed to capture various graph signal structures through a highly adaptive kernel that incorporates a flexible polynomial function in the graph spectral domain. Unlike most existing approaches, we propose to learn such a spectral kernel, where the polynomial setup enables learning without the need for eigen-decomposition of the graph Laplacian. In addition, this kernel has the interpretability of graph filtering achieved by a bespoke maximum likelihood learning algorithm that enforces the positivity of the spectrum. We demonstrate the interpretability of the model in synthetic experiments from which we show the various ground truth spectral filters can be accurately recovered, and the adaptability translates to superior performances in the prediction of real-world graph data of various characteristics.

Unsupervised discretization is a crucial step in many knowledge discovery tasks. The state-of-the-art method for one-dimensional data infers locally adaptive histograms using the minimum description length (MDL) principle, but the multi-dimensional case is far less studied: current methods consider the dimensions one at a time (if not independently), which result in discretizations based on rectangular cells of adaptive size. Unfortunately, this approach is unable to adequately characterize dependencies among dimensions and/or results in discretizations consisting of more cells (or bins) than is desirable. To address this problem, we propose an expressive model class that allows for far more flexible partitions of two-dimensional data. We extend the state of the art for the one-dimensional case to obtain a model selection problem based on the normalised maximum likelihood, a form of refined MDL. As the flexibility of our model class comes at the cost of a vast search space, we introduce a heuristic algorithm, named PALM, which partitions each dimension alternately and then merges neighbouring regions, all using the MDL principle. Experiments on synthetic data show that PALM 1) accurately reveals ground truth partitions that are within the model class (i.e., the search space), given a large enough sample size; 2) approximates well a wide range of partitions outside the model class; 3) converges, in contrast to its closest competitor IPD; and 4) is self-adaptive with regard to both sample size and local density structure of the data despite being parameter-free. Finally, we apply our algorithm to two geographic datasets to demonstrate its real-world potential.

Model-Agnostic Meta-Learning (MAML) has demonstrated widespread success in training models that can quickly adapt to new tasks via one or few stochastic gradient descent steps. However, the MAML objective is significantly more difficult to optimize compared to standard Empirical Risk Minimization (ERM), and little is understood about how much MAML improves over ERM in terms of the fast adaptability of their solutions in various scenarios. We analytically address this issue in a linear regression setting consisting of a mixture of easy and hard tasks, where hardness is determined by the number of gradient steps required to solve the task. Specifically, we prove that for $\Omega(d_{\text{eff}})$ labelled test samples (for gradient-based fine-tuning) where $d_{\text{eff}}$ is the effective dimension of the problem, in order for MAML to achieve substantial gain over ERM, the optimal solutions of the hard tasks must be closely packed together with the center far from the center of the easy task optimal solutions. We show that these insights also apply in a low-dimensional feature space when both MAML and ERM learn a representation of the tasks, which reduces the effective problem dimension. Further, our few-shot image classification experiments suggest that our results generalize beyond linear regression.

In recent years, the success of deep learning has inspired many researchers to study the optimization of general smooth non-convex functions. However, recent works have established pessimistic worst-case complexities for this class functions, which is in stark contrast with their superior performance in real-world applications (e.g. training deep neural networks). On the other hand, it is found that many popular non-convex optimization problems enjoy certain structured properties which bear some similarities to convexity. In this paper, we study the class of \textit{quasar-convex functions} to close the gap between theory and practice. We study the convergence of first order methods in a variety of different settings and under different optimality criterions. We prove complexity upper bounds that are similar to standard results established for convex functions and much better that state-of-the-art convergence rates of non-convex functions. Overall, this paper suggests that \textit{quasar-convexity} allows efficient optimization procedures, and we are looking forward to seeing more problems that demonstrate similar properties in practice.

Convex optimization problems with staged structure appear in several contexts, including optimal control, verification of deep neural networks, and isotonic regression. Off-the-shelf solvers can solve these problems but may scale poorly. We develop a nonconvex reformulation designed to exploit this staged structure. Our reformulation has only simple bound constraints, enabling solution via projected gradient methods and their accelerated variants. The method automatically generates a sequence of primal and dual feasible solutions to the original convex problem, making optimality certification easy. We establish theoretical properties of the nonconvex formulation, showing that it is (almost) free of spurious local minima and has the same global optimum as the convex problem. We modify PGD to avoid spurious local minimizers so it always converges to the global minimizer. For neural network verification, our approach obtains small duality gaps in only a few gradient steps. Consequently, it can quickly solve large-scale verification problems faster than both off-the-shelf and specialized solvers.