Kevin Regan

I currently work at Google where I focus on very large scale machine learning for ad click prediction. I recently completed Google's Machine Learning Ninja program where worked on models for facial recognition, and investigated large margin methods for deep learning (published at NeuIPS 2018). My doctoral work focused on preference elicitation tech... niques for sequential decision makingand intersects Decision Making, Probablistic Modeling, Machine Learning and Optimization. Optimization in machine learning, both theoretical and applied, is presently dominated by first-order gradient methods such as stochastic gradient descent. Second-order optimization methods that involve second-order derivatives and/or second-order statistics of the data have become far less prevalent despite strong theoretical properties, due to their prohibitive computation, memory and communication costs. In an attempt to bridge this gap between theoretical and practical optimization, we present a proof-of-concept distributed system implementation of a second-order preconditioned method (specifically, a variant of full-matrix Adagrad), that along with a few yet critical algorithmic and numerical improvements, provides significant practical gains in convergence on state-of-the-art deep models and gives rise to actual wall-time improvements in practice compared to conventional first-order methods. Our design effectively utilizes the prevalent heterogeneous hardware architecture for training deep models which consists of a multicore CPU coupled with multiple accelerator units. We demonstrate superior performance on very large learning problems in machine translation where our distributed implementation runs considerably faster than existing gradient-based methods. We present a formulation of deep learning that aims at producing a large margin classifier. The notion of margin, minimum distance to a decision boundary, has served as the foundation of several theoretically profound and empirically suc- cessful results for both classification and ...Read More