Learning and optimization in the face of data perturbations

Thesis: Ph. D., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, May, 2020Cataloged from the official PDF of thesis.Includes bibliographical references (pages 145-163).Many problems in the machine learning pipeline boil down to maximizing the expectation of a function over a distribution. This is the classic problem of stochastic optimization. There are two key challenges in solving such stochastic optimization problems: 1) the function is often non-convex, making optimization difficult; 2) the distribution is not known exactly, but may be perturbed adversarially or is otherwise obscured. Each issue is individually so challenging to warrant a substantial accompanying body of work addressing it, but addressing them simultaneously remains difficult. This thesis addresses problems at the intersection of non-convexity and data perturbations. We study the intersection of the two issues along two dual lines of inquiry: first, we build perturbation-aware algorithms with guarantees for non-convex problems; second, we seek to understand how data perturbations can be leveraged to enhance non-convex optimization algorithms. Along the way, we will study new types of data perturbations and seek to understand their connection to generalization.by Matthew James Staib.Ph. D.Ph.D. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Scienc