# Accelerated Extra-Gradient Descent: A Novel Accelerated First-Order Method

arXiv: https://arxiv.org/abs/1706.04680 · HTML: https://mlsanity.com/paper/1706.04680/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jun 2017.

## Built on by (most cited first, 8 of 8)

- [No-Regret Dynamics in the Fenchel Game: A Unified Framework for Algorithmic Convex Optimization](https://mlsanity.com/paper/2111.11309/) (2021)
- [Complementary Composite Minimization, Small Gradients in General Norms, and Applications](https://mlsanity.com/paper/2101.11041/) (2021)
- [Extra-Newton: A First Approach to Noise-Adaptive Accelerated Second-Order Methods](https://mlsanity.com/paper/2211.01832/) (2022)
- [Revisiting the Role of Euler Numerical Integration on Acceleration and Stability in Convex Optimization](https://mlsanity.com/paper/2102.11537/) (2021)
- [Accelerated Preference Optimization for Large Language Model Alignment](https://mlsanity.com/paper/2410.06293/) (2024)
- [Potential Function-based Framework for Making the Gradients Small in Convex and Min-Max Optimization](https://mlsanity.com/paper/2101.12101/) (2021)
- [Accelerated Riemannian Optimization: Handling Constraints with a Prox to Bound Geometric Penalties](https://mlsanity.com/paper/2211.14645/) (2022)
- [Understanding Riemannian Acceleration via a Proximal Extragradient Framework](https://mlsanity.com/paper/2111.02763/) (2021)

## Abstract (arXiv)

We provide a novel accelerated first-order method that achieves the asymptotically optimal convergence rate for smooth functions in the first-order oracle model. To this day, Nesterov's Accelerated Gradient Descent (AGD) and variations thereof were the only methods achieving acceleration in this standard blackbox model. In contrast, our algorithm is significantly different from AGD, as it relies on a predictor-corrector approach similar to that used by Mirror-Prox [Nemirovski, 2004] and Extra-Gradient Descent [Korpelevich, 1977] in the solution of convex-concave saddle point problems. For this reason, we dub our algorithm Accelerated Extra-Gradient Descent (AXGD). Its construction is motivated by the discretization of an accelerated continuous-time dynamics [Krichene et al., 2015] using the classical method of implicit Euler discretization. Our analysis explicitly shows the effects of discretization through a conceptually novel primal-dual viewpoint. Moreover, we show that the method is quite general: it attains optimal convergence rates for other classes of objectives (e.g., those with generalized smoothness properties or that are non-smooth and Lipschitz-continuous) using the appropriate choices of step lengths. Finally, we present experiments showing that our algorithm matches the performance of Nesterov's method, while appearing more robust to noise in some cases.