Video: https://vimeo.com/183315365 Projected gradient descent (PGD), and its close variants, are often considered the method of choice for solving a very large variety of machine learning optimization problems, including sparse recovery problems, empirical risk minimization, stochastic optimization, and online convex optimization. This is not surprising, since PGD is often optimal …
Video: https://vimeo.com/154897631 We use CVaR to create a general framework for computing compromise solutions in a multi-objective, multi-stakeholder setting. In this setting, we sample the preferences of a population of stakeholders and we observe that the stakeholder dissatisfactions (distance to their utopia points) can be interpreted as random variables. Consequently, …
Video Recording: https://vimeo.com/153826086 Our quest is to derive convex relaxations for the pooling problem, a nonconvex production planning problem in which products are mixed in intermediate pools in order to meet quality targets at their destinations. The story begins with a description of the problem and discussion of state-of-the-art solution …
Video Recording: https://vimeo.com/154227289 We are in the midst of a 3D revolution. Robots enabled by 3D cameras are beginning to autonomously drive cars, perform surgeries, and manage factories. However, when deployed in the real-world, these cameras face several challenges that prevent them from measuring 3D shape reliably. These challenges include …
A Matrix Factorization Approach to Multiple Imputation: https://vimeo.com/155397341 Almost all empirical analysis in the social sciences is plagued with the problem of missing data, for instance in opinion surveys, some respondents choose not to answer certain questions, or in longitudnal surveys respondents in the pilot round may drop out in …
Video: https://vimeo.com/156600995 We introduce the Stochastic Monotone Aggregated Root-Finding (SMART) algorithm, a new randomized operator-splitting scheme for finding roots of finite sums of operators. These algorithms are similar to the growing class of incremental aggregated gradient algorithms, which minimize finite sums of functions; the difference is that we replace gradients …
video: https://vimeo.com/156713270 In the first part of the talk we state how geometry can be used for modeling mixtures of subspaces as well as analyzing online (stochastic) optimization algorithms. We introduce a Bayesian model for inferring mixtures of subspaces of different dimensions. The key challenge in such a model is …
Video: https://vimeo.com/158060000 We present our recent progress on adopting control tools for optimization of strongly convex functions. First, built upon the existing integral quadratic constraint (IQC) analysis framework of first-order optimization methods, we further develop an IQC approach to analyze the stochastic average gradient (SAG) method. The SAG method is …
Video: https://vimeo.com/158493334 Talk 1 – Kwang-Sung Jun: Top Arm Identification in Multi-Armed Bandits with Batch Arm Pulls We introduce a new multi-armed bandit (MAB) problem in which arms must be sampled in batches, rather than one at a time. This is motivated by applications in social media monitoring and biological …
Video: https://vimeo.com/159423831 Robust statistics provides a powerful framework for quantifying the behavior of estimators when data are observed subject to imperfections that deviate from standard modeling assumptions. In this talk, we highlight recent work involving statistical theory for robust estimators in high dimensions, with applications to compressed sensing and graphical …