- Full text PDF available (4)
We introduce a generic scheme for accelerating first-order optimization methods in the sense of Nesterov, which builds upon a new analysis of the accelerated prox-imal point algorithm. Our approach consists of minimizing a convex objective by approximately solving a sequence of well-chosen auxiliary problems, leading to faster convergence. This strategy… (More)
Matrine (MAT) is an active alkaloid extracted from Radix Sophora flavescens. The present study was to investigate whether MAT could effectively treat Adriamycin-induced nephropathy (AIN). AIN was induced in rats using a single injection of Adriamycin (ADR). Renal interleukin-6 (IL-6), IL-10, IL-17 and transforming growth factor-β (TGF-β) levels, and the… (More)
Consider the minimization of a large sum of convex functions min x∈R d f (x) △ = 1 n n i=1 f i (x) + ψ(x) , where each f i is smooth and convex and ψ is a convex regularization penalty but not necessarily differentiable.
References A. Agarwal and L. Bottou. A lower bound for the optimization of finite sums. Technical report, Saga: A fast incremental gradient method with support for non-strongly convex composite objectives.regularizing: approximate proximal point and faster stochastic algorithms for empirical risk minimization. In ICML, 2015. Efficient algorithms for… (More)
We propose an approach to accelerate gradient-based optimization algorithms by giving them the ability to exploit curvature information using quasi-Newton update rules. The proposed scheme, called QuickeNing, is generic and can be applied to a large class of first-order methods such as incremental and block-coordinate algorithms; it is also compatible with… (More)