2024/07/03 by Zhiqi Bu, Bu, Zhiqi, Shiyun Xu +1 · 2 citations
Engineering · Mathematics · #Advanced Numerical Analysis Techniques #Computation and Language (cs.CL) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Iterative Methods for Nonlinear Equations #Machine Learning (cs.LG) #Reservoir Engineering and Simulation Methods
paper · pdf · doi:10.48550/arxiv.2407.02772
openalex publication_date 2024/07/03 · openalex created_date 2024/07/06 · openalex updated_date 2026/07/28
We propose the generalized Newton's method (GeN) -- a Hessian-informed approach that applies to any optimizer such as SGD and Adam, and covers the Newton-Raphson method as a sub-case. Our method automatically and dynamically selects the learning rate that accelerates the convergence, without the intensive tuning of the learning rate scheduler. In practice, our method is easily implementable, since it only requires additional forward passes with almost zero computational overhead (in terms of training time and memory cost), if the overhead is amortized over many iterations. We present extensive experiments on language and vision tasks (e.g. GPT and ResNet) to showcase that GeN optimizers match the state-of-the-art performance, which was achieved with carefully tuned learning rate schedulers.