# Parallel Architecture and Hyperparameter Search via Successive Halving and Classification

arXiv: https://arxiv.org/abs/1805.10255 · HTML: https://mlsanity.com/paper/1805.10255/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 May 2018.

## Built on by (most cited first, 5 of 5)

- [Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies](https://mlsanity.com/paper/2112.13835/) (2021)
- [SOLO: Search Online, Learn Offline for Combinatorial Optimization Problems](https://mlsanity.com/paper/2104.01646/) (2021)
- [Multi-objective Optimization by Learning Space Partitions](https://mlsanity.com/paper/2110.03173/) (2021)
- [Differentiable Multi-Fidelity Fusion: Efficient Learning of Physics Simulations with Neural Architecture Search and Transfer Learning](https://mlsanity.com/paper/2306.06904/) (2023)
- [Efficient Hyperparameter Search for Non-Stationary Model Training](https://mlsanity.com/paper/2512.01258/) (2025)

## Abstract (arXiv)

We present a simple and powerful algorithm for parallel black box optimization called Successive Halving and Classification (SHAC). The algorithm operates in K stages of parallel function evaluations and trains a cascade of binary classifiers to iteratively cull the undesirable regions of the search space. SHAC is easy to implement, requires no tuning of its own configuration parameters, is invariant to the scale of the objective function and can be built using any choice of binary classifier. We adopt tree-based classifiers within SHAC and achieve competitive performance against several strong baselines for optimizing synthetic functions, hyperparameters and architectures.