Skip to yearly menu bar Skip to main content


Poster

Doubly Adaptive Scaled Algorithm for Machine Learning Using Second-Order Information

Majid Jahani · Sergey Rusakov · Zheng Shi · Peter Richtarik · Michael W Mahoney · Martin Takac

Keywords: [ non-convex optimization ] [ deep learning ] [ second-order optimization ] [ stochastic optimization ] [ convex optimization ]


Abstract:

We present a novel adaptive optimization algorithm for large-scale machine learning problems. Equipped with a low-cost estimate of local curvature and Lipschitz smoothness, our method dynamically adapts the search direction and step-size. The search direction contains gradient information preconditioned by a well-scaled diagonal preconditioning matrix that captures the local curvature information. Our methodology does not require the tedious task of learning rate tuning, as the learning rate is updated automatically without adding an extra hyper-parameter. We provide convergence guarantees on a comprehensive collection of optimization problems, including convex, strongly convex, and nonconvex problems, in both deterministic and stochastic regimes. We also conduct an extensive empirical evaluation on standard machine learning problems, justifying our algorithm's versatility and demonstrating its strong performance compared to other start-of-the-art first-order and second-order methods.

Chat is not available.