The condition number of a differentiable convex function, namely the ratio of its smoothness to strong convexity constants, is closely tied to fundamental properties of the function. In …
In this paper, we propose a Distributed Accumulated Newton Conjugate gradiEnt (DANCE) method in which sample size is gradually increasing to quickly obtain a solution whose …
T Yu, XW Liu, YH Dai, J Sun - IEEE Transactions on Neural …, 2020 - ieeexplore.ieee.org
We consider the problem of minimizing the sum of an average of a large number of smooth convex component functions and a possibly nonsmooth convex function that admits a simple …
This work presents a new optimization algorithm for empirical risk minimization. The algorithm bridges the gap between first-and second-order methods by computing a search …
The condition number of a smooth convex function, namely the ratio of its smoothness to strong convexity constants, is closely tied to fundamental properties of the function. In …
Le present expose decrit une methode experimentale, concue dans le but de determiner les caracteristiques de fuite d'air des murs exterieurs d'un Bdifice. Cette methode consiste B …
In this work1, we propose a Distributed Accumulated Newton Conjugate gradiEnt (DANCE) method in which sample size is gradually increasing to quickly obtain a solution whose …
This thesis focuses on three themes related to the mathematical theory of first-order methods for convex minimization: acceleration, conditioning, and rescaling. Chapters 1 and 2 explore …