# Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian

arXiv: https://arxiv.org/abs/2011.06505 · HTML: https://mlsanity.com/paper/2011.06505/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Nov 2020.

## Built on by (most cited first, 20 of 20)

- [Diversify and Disambiguate: Learning From Underspecified Data](https://mlsanity.com/paper/2202.03418/) (2022)
- [K-level Reasoning for Zero-Shot Coordination in Hanabi](https://mlsanity.com/paper/2207.07166/) (2022)
- [Quantification of Uncertainty with Adversarial Models](https://mlsanity.com/paper/2307.03217/) (2023)
- [Predicting is not Understanding: Recognizing and Addressing Underspecification in Machine Learning](https://mlsanity.com/paper/2207.02598/) (2022)
- [Continuously Discovering Novel Strategies via Reward-Switching Policy Optimization](https://mlsanity.com/paper/2204.02246/) (2022)
- [Equivariant Networks for Zero-Shot Coordination](https://mlsanity.com/paper/2210.12124/) (2022)
- [Heterogeneous Multi-agent Zero-Shot Coordination by Coevolution](https://mlsanity.com/paper/2208.04957/) (2022)
- [Learning General World Models in a Handful of Reward-Free Deployments](https://mlsanity.com/paper/2210.12719/) (2022)
- [Task Discovery: Finding the Tasks that Neural Networks Generalize on](https://mlsanity.com/paper/2212.00261/) (2022)
- [Lyapunov Exponents for Diversity in Differentiable Games](https://mlsanity.com/paper/2112.14570/) (2021)
- [On-the-fly Strategy Adaptation for ad-hoc Agent Coordination](https://mlsanity.com/paper/2203.08015/) (2022)
- [Mix-ME: Quality-Diversity for Multi-Agent Learning](https://mlsanity.com/paper/2311.01829/) (2023)
- [Learning to Optimize Quasi-Newton Methods](https://mlsanity.com/paper/2210.06171/) (2022)
- [Iteratively Learn Diverse Strategies with State Distance Information](https://mlsanity.com/paper/2310.14509/) (2023)
- [Sharpness-diversity tradeoff: improving flat ensembles with SharpBalance](https://mlsanity.com/paper/2407.12996/) (2024)
- [Stein Variational Evolution Strategies](https://mlsanity.com/paper/2410.10390/) (2024)
- [Differentiable Arbitrating in Zero-sum Markov Games](https://mlsanity.com/paper/2302.10058/) (2023)
- [GDA-AM: On the effectiveness of solving minimax optimization via Anderson Acceleration](https://mlsanity.com/paper/2110.02457/) (2021)
- [Policy Dispersion in Non-Markovian Environment](https://mlsanity.com/paper/2302.14509/) (2023)
- [ACE and Diverse Generalization via Selective Disagreement](https://mlsanity.com/paper/2509.07955/) (2025)

## Abstract (arXiv)

Over the last decade, a single algorithm has changed many facets of our lives - Stochastic Gradient Descent (SGD). In the era of ever decreasing loss functions, SGD and its various offspring have become the go-to optimization tool in machine learning and are a key component of the success of deep neural networks (DNNs). While SGD is guaranteed to converge to a local optimum (under loose assumptions), in some cases it may matter which local optimum is found, and this is often context-dependent. Examples frequently arise in machine learning, from shape-versus-texture-features to ensemble methods and zero-shot coordination. In these settings, there are desired solutions which SGD on 'standard' loss functions will not find, since it instead converges to the 'easy' solutions. In this paper, we present a different approach. Rather than following the gradient, which corresponds to a locally greedy direction, we instead follow the eigenvectors of the Hessian, which we call "ridges". By iteratively following and branching amongst the ridges, we effectively span the loss surface to find qualitatively different solutions. We show both theoretically and experimentally that our method, called Ridge Rider (RR), offers a promising direction for a variety of challenging problems.