Zhuang, ZhenxunCutkosky, AshokOrabona, Francesco2020-05-152020-05-152019-06-10Zhenxun Zhuang, Ashok Cutkosky, Francesco Orabona. 2019. "Surrogate Losses for Online Learning of Stepsizes in Stochastic Non-Convex Optimization." International Conference on Machine Learninghttps://hdl.handle.net/2144/40899Stochastic Gradient Descent (SGD) has played a central role in machine learning. However, it requires a carefully hand-picked stepsize for fast convergence, which is notoriously tedious and time-consuming to tune. Over the last several years, a plethora of adaptive gradient-based algorithms have emerged to ameliorate this problem. In this paper, we propose new surrogate losses to cast the problem of learning the optimal stepsizes for the stochastic optimization of a non-convex smooth objective function onto an online convex optimization problem. This allows the use of noregret online algorithms to compute optimal stepsizes on the fly. In turn, this results in a SGD algorithm with self-tuned stepsizes that guarantees convergence rates that are automatically adaptive to the level of noise.en-USCopyright 2019 by the author(s).Conference materials546358