# Stochastic Maximum Likelihood Optimization via Hypernetworks

arXiv: https://arxiv.org/abs/1712.01141 · HTML: https://mlsanity.com/paper/1712.01141/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Dec 2017.

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

- [HyperShot: Few-Shot Learning by Kernel HyperNetworks](https://mlsanity.com/paper/2203.11378/) (2022)
- [HyperPocket: Generative Point Cloud Completion](https://mlsanity.com/paper/2102.05973/) (2021)
- [Points2NeRF: Generating Neural Radiance Fields from 3D point cloud](https://mlsanity.com/paper/2206.01290/) (2022)
- [HyperNeRFGAN: Hypernetwork approach to 3D NeRF GAN](https://mlsanity.com/paper/2301.11631/) (2023)
- [Modeling 3D Surface Manifolds with a Locally Conditioned Atlas](https://mlsanity.com/paper/2102.05984/) (2021)
- [Forecasting with Hyper-Trees](https://mlsanity.com/paper/2405.07836/) (2024)
- [As Good as It KAN Get: High-Fidelity Audio Representation](https://mlsanity.com/paper/2503.02585/) (2025)

## Abstract (arXiv)

This work explores maximum likelihood optimization of neural networks through hypernetworks. A hypernetwork initializes the weights of another network, which in turn can be employed for typical functional tasks such as regression and classification. We optimize hypernetworks to directly maximize the conditional likelihood of target variables given input. Using this approach we obtain competitive empirical results on regression and classification benchmarks.