paper-with-me

Papers

Nesterov's Accelerated Gradient and Momentum as approximations to Regularised Update Descent

2016-07-07 · Aleksandar Botev, Guy Lever, David Barber

We present a unifying framework for adapting the update direction in gradient-based iterative optimization methods. As natural special cases we re-derive classical momentum and Nesterov's accelerated gradient method, lending a new intuitive interpretation to the latter algorithm. We show that a new algorithm, which we term Regularised Gradient Descent, can converge more quickly than either Nesterov's algorithm or the classical momentum algorithm.

📄 PDF Abstract BibTeX arXiv:1607.01981

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A modified limited memory Nesterov's accelerated quasi-Newton

2021-12-01 · S. Indrapriyadarsini, Shahrzad Mahboubi, Hiroshi Ninomiya, Takeshi Kamio 외

The Nesterov's accelerated quasi-Newton (L)NAQ method has shown to accelerate the conventional (L)BFGS quasi-Newton method using the Nesterov's accelerated gradient in several neural network (NN) applications. However, t…

Momentum-based gradient descent methods for Lie groups

2024-04-14 · Cédric M. Campos, David Martín de Diego, José Torrente

Polyak's Heavy Ball (PHB; Polyak, 1964), a.k.a. Classical Momentum, and Nesterov's Accelerated Gradient (NAG; Nesterov, 1983) are well know examples of momentum-descent methods for optimization. While the latter outperfo…

On the Convergence of Nesterov's Accelerated Gradient Method in Stochastic Settings

2020-02-27 · ICML 2020 1 · Mahmoud Assran, Michael Rabbat

We study Nesterov's accelerated gradient method with constant step-size and momentum parameters in the stochastic approximation setting (unbiased gradients with bounded variance) and the finite-sum setting (where randomn…

Robust Gradient Descent via Heavy-Ball Momentum with Predictive Extrapolation

2025-12-10 · Sarwan Ali arxiv

Accelerated gradient methods like Nesterov's Accelerated Gradient (NAG) achieve faster convergence on well-conditioned problems but often diverge on ill-conditioned or non-convex landscapes due to aggressive momentum acc…

Provable Accelerated Convergence of Nesterov's Momentum for Deep ReLU Neural Networks

2023-06-13 · Fangshuo Liao, Anastasios Kyrillidis

Current state-of-the-art analyses on the convergence of gradient descent for training neural networks focus on characterizing properties of the loss landscape, such as the Polyak-Lojaciewicz (PL) condition and the restri…

Open-Ended Question Answering