# Randomized gradient-free methods in convex optimization

arXiv: https://arxiv.org/abs/2211.13566 · HTML: https://mlsanity.com/paper/2211.13566/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2022.

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

- [MINI-LLM: Memory-Efficient Structured Pruning for Large Language Models](https://mlsanity.com/paper/2407.11681/) (2024)
- [Enhancing variational quantum algorithms by balancing training on classical and quantum hardware](https://mlsanity.com/paper/2503.16361/) (2025)
- [On the Optimal Construction of Unbiased Gradient Estimators for Zeroth-Order Optimization](https://mlsanity.com/paper/2510.19953/) (2025)
- [Federated Learning Can Find Friends That Are Advantageous](https://mlsanity.com/paper/2402.05050/) (2024)
- [Inverting Black-Box Face Recognition Systems via Zero-Order Optimization in Eigenface Space](https://mlsanity.com/paper/2506.09777/) (2025)
- [Learning Local Stackelberg Equilibria from Repeated Interactions with a Learning Agent](https://mlsanity.com/paper/2510.22471/) (2025)
- [Wall-Clock Complexity for Zeroth-Order Optimization with Tunable Oracle Fidelity](https://mlsanity.com/paper/2605.31346/) (2026)

## Abstract (arXiv)

This review presents modern gradient-free methods to solve convex optimization problems. By gradient-free methods, we mean those that use only (noisy) realizations of the objective value. We are motivated by various applications where gradient information is prohibitively expensive or even unavailable. We mainly focus on three criteria: oracle complexity, iteration complexity, and the maximum permissible noise level.