paper-with-me

Papers

Parametrized Accelerated Methods Free of Condition Number

2018-02-28 · Chaoyue Liu, Mikhail Belkin

Analyses of accelerated (momentum-based) gradient descent usually assume bounded condition number to obtain exponential convergence rates. However, in many real problems, e.g., kernel methods or deep neural networks, the condition number, even locally, can be unbounded, unknown or mis-estimated. This poses problems in both implementing and analyzing accelerated algorithms. In this paper, we address this issue by proposing parametrized accelerated methods by considering the condition number as a free parameter. We provide spectral-level analysis for several important accelerated algorithms, obtain explicit expressions and improve worst case convergence rates. Moreover, we show that those algorithm converge exponentially even when the condition number is unknown or mis-estimated.

📄 PDF Abstract BibTeX arXiv:1802.10235

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Conditional Accelerated Lazy Stochastic Gradient Descent

2017-03-16 · ICML 2017 8 · Guanghui Lan, Sebastian Pokutta, Yi Zhou, Daniel Zink

In this work we introduce a conditional accelerated lazy stochastic gradient descent algorithm with optimal number of calls to a stochastic first-order oracle and convergence rate $O\left(\frac{1}{\varepsilon^2}\right)$ …

On exponential convergence of SGD in non-convex over-parametrized learning

2018-11-06 · Raef Bassily, Mikhail Belkin, Siyuan Ma

Large over-parametrized models learned via stochastic gradient descent (SGD) methods have become a key element in modern machine learning. Although SGD methods are very effective in practice, most theoretical analyses of…

BIG-bench Machine Learning

Bayesian Free Energy of Deep ReLU Neural Network in Overparametrized Cases

2023-03-28 · Shuya Nagayasu, Sumio Watanabe

In many research fields in artificial intelligence, it has been shown that deep neural networks are useful to estimate unknown functions on high dimensional input spaces. However, their generalization performance is not …

Learning Theory

Parameter-free Locally Accelerated Conditional Gradients

2021-02-12 · Alejandro Carderera, Jelena Diakonikolas, Cheuk Yin Lin, Sebastian Pokutta

Projection-free conditional gradient (CG) methods are the algorithms of choice for constrained optimization setups in which projections are often computationally prohibitive but linear optimization over the constraint se…

Adaptive Gradient Methods for Constrained Convex Optimization and Variational Inequalities

2020-07-17 · Alina Ene, Huy L. Nguyen, Adrian Vladu

We provide new adaptive first-order methods for constrained convex optimization. Our main algorithms AdaACSA and AdaAGD+ are accelerated methods, which are universal in the sense that they achieve nearly-optimal converge…