# Inexact Model: A Framework for Optimization and Variational Inequalities

arXiv: https://arxiv.org/abs/1902.00990 · HTML: https://mlsanity.com/paper/1902.00990/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Feb 2019.

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

- [Smooth Monotone Stochastic Variational Inequalities and Saddle Point Problems: A Survey](https://mlsanity.com/paper/2208.13592/) (2022)
- [First-Order Methods for Convex Optimization](https://mlsanity.com/paper/2101.00935/) (2021)
- [Adaptive first-order methods revisited: Convex optimization without Lipschitz requirements](https://mlsanity.com/paper/2107.08011/) (2021)
- [Adaptive proximal gradient methods are universal without approximation](https://mlsanity.com/paper/2402.06271/) (2024)
- [Analysis of Kernel Mirror Prox for Measure Optimization](https://mlsanity.com/paper/2403.00147/) (2024)
- [Near-Optimal Convergence of Accelerated Gradient Methods under Generalized and (L0, L1)-Smoothness](https://mlsanity.com/paper/2508.06884/) (2025)
- [The Hidden Cost of Approximation in Online Mirror Descent](https://mlsanity.com/paper/2511.22283/) (2025)
- [Wall-Clock Complexity for Zeroth-Order Optimization with Tunable Oracle Fidelity](https://mlsanity.com/paper/2605.31346/) (2026)

## Abstract (arXiv)

In this paper we propose a general algorithmic framework for first-order methods in optimization in a broad sense, including minimization problems, saddle-point problems and variational inequalities. This framework allows to obtain many known methods as a special case, the list including accelerated gradient method, composite optimization methods, level-set methods, proximal methods. The idea of the framework is based on constructing an inexact model of the main problem component, i.e. objective function in optimization or operator in variational inequalities. Besides reproducing known results, our framework allows to construct new methods, which we illustrate by constructing a universal method for variational inequalities with composite structure. This method works for smooth and non-smooth problems with optimal complexity without a priori knowledge of the problem smoothness. We also generalize our framework for strongly convex objectives and strongly monotone variational inequalities.