# Understanding Nesterov's Acceleration via Proximal Point Method

arXiv: https://arxiv.org/abs/2005.08304 · HTML: https://mlsanity.com/paper/2005.08304/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 May 2020.

## Built on by (most cited first, 7 of 7)

- [Convergence and Stability of the Stochastic Proximal Point Algorithm with Momentum](https://mlsanity.com/paper/2111.06171/) (2021)
- [Stacking as Accelerated Gradient Descent](https://mlsanity.com/paper/2403.04978/) (2024)
- [Accelerated Preference Optimization for Large Language Model Alignment](https://mlsanity.com/paper/2410.06293/) (2024)
- [The Ball-Proximal (="Broximal") Point Method: a New Algorithm, Convergence Theory, and Applications](https://mlsanity.com/paper/2502.02002/) (2025)
- [A Variational Perspective on High-Resolution ODEs](https://mlsanity.com/paper/2311.02002/) (2023)
- [On the stability of gradient descent with second order dynamics for time-varying cost functions](https://mlsanity.com/paper/2405.13765/) (2024)
- [A Catalyst Framework for the Quantum Linear System Problem via the Proximal Point Algorithm](https://mlsanity.com/paper/2406.13879/) (2024)

## Abstract (arXiv)

The proximal point method (PPM) is a fundamental method in optimization that is often used as a building block for designing optimization algorithms. In this work, we use the PPM method to provide conceptually simple derivations along with convergence analyses of different versions of Nesterov's accelerated gradient method (AGM). The key observation is that AGM is a simple approximation of PPM, which results in an elementary derivation of the update equations and stepsizes of AGM. This view also leads to a transparent and conceptually simple analysis of AGM's convergence by using the analysis of PPM. The derivations also naturally extend to the strongly convex case. Ultimately, the results presented in this paper are of both didactic and conceptual value; they unify and explain existing variants of AGM while motivating other accelerated methods for practically relevant settings.