paper-with-me

Papers

Modified online Newton step based on element wise multiplication

2019-04-11 · Charanjeet, Anuj Sharma

The second order method as Newton Step is a suitable technique in Online Learning to guarantee regret bound. The large data is a challenge in Newton method to store second order matrices as hessian. In this paper, we have proposed an modified online Newton step that store first and second order matrices of dimension m (classes) by d (features). we have used element wise arithmetic operation to retain matrices size same. The modified second order matrix size results in faster computations. Also, the mistake rate is at par with respect to popular methods in literature. The experiments outcome indicate that proposed method could be helpful to handle large multi class datasets in common desktop machines using second order method as Newton step.

📄 PDF Abstract BibTeX arXiv:1904.05633

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Valuation of the Convertible Bonds under Penalty TF model using Finite Element Method

2023-01-25 · Rakhymzhan Kazbek, Yogi Erlangga, Yerlan Amanbek, Dongming Wei

In this paper, the TF system of two-coupled Black-Scholes equations for pricing the convertible bonds is solved numerically by using the P1 and P2 finite elements with the inequality constraints approximated by the penal…

Improving Pseudo-Time Stepping Convergence for CFD Simulations With Neural Networks

2023-10-10 · Anouk Zandbergen, Tycho van Noorden, Alexander Heinlein

Computational fluid dynamics (CFD) simulations of viscous fluids described by the Navier-Stokes equations are considered. Depending on the Reynolds number of the flow, the Navier-Stokes equations may exhibit a highly non…

NeST-BO: Fast Local Bayesian Optimization via Newton-Step Targeting of Gradient and Hessian Information

2025-10-07 · Wei-Ting Tang, Akshay Kudva, Joel A. Paulson arxiv

Bayesian optimization (BO) is effective for expensive black-box problems but remains challenging in high dimensions. We propose NeST-BO, a curvature-aware local BO method that targets a (modified) Newton step by jointly …

SNAP: A semismooth Newton algorithm for pathwise optimization with optimal local convergence rate and oracle properties

2018-10-09 · Jian Huang, Yuling Jiao, Xiliang Lu, Yueyong Shi 외

We propose a semismooth Newton algorithm for pathwise optimization (SNAP) for the LASSO and Enet in sparse, high-dimensional linear regression. SNAP is derived from a suitable formulation of the KKT conditions based on N…

regression

A fast neural hybrid Newton solver adapted to implicit methods for nonlinear dynamics

2024-07-04 · Tianyu Jin, Georg Maierhofer, Katharina Schratz, Yang Xiang

The use of implicit time-stepping schemes for the numerical approximation of solutions to stiff nonlinear time-evolution equations brings well-known advantages including, typically, better stability behaviour and corresp…

Operator learning