# Lottery Tickets in Evolutionary Optimization: On Sparse Backpropagation-Free Trainability

arXiv: https://arxiv.org/abs/2306.00045 · HTML: https://mlsanity.com/paper/2306.00045/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 48 references that are in the map.
- First posted on arXiv 31 May 2023.

## Builds on (most cited first, 25 of 25)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Visualizing the Loss Landscape of Neural Nets](https://mlsanity.com/paper/1712.09913/) (2017)
- [Linear Mode Connectivity and the Lottery Ticket Hypothesis](https://mlsanity.com/paper/1912.05671/) (2019)
- [Evolution Strategies as a Scalable Alternative to Reinforcement Learning](https://mlsanity.com/paper/1703.03864/) (2017)
- [Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation](https://mlsanity.com/paper/2106.13281/) (2021)
- [Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science](https://mlsanity.com/paper/1707.04780/) (2017)
- [The Lottery Ticket Hypothesis for Pre-trained BERT Networks](https://mlsanity.com/paper/2007.12223/) (2020)
- [Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask](https://mlsanity.com/paper/1905.01067/) (2019)
- [Characterising Bias in Compressed Models](https://mlsanity.com/paper/2010.03058/) (2020)
- [Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning](https://mlsanity.com/paper/1712.06567/) (2017)
- [A Unified Lottery Ticket Hypothesis for Graph Neural Networks](https://mlsanity.com/paper/2102.06790/) (2021)
- [The Early Phase of Neural Network Training](https://mlsanity.com/paper/2002.10365/) (2020)
- [One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers](https://mlsanity.com/paper/1906.02773/) (2019)
- [Gradient Flow in Sparse Neural Networks and How Lottery Tickets Win](https://mlsanity.com/paper/2010.03533/) (2020)
- [Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLP](https://mlsanity.com/paper/1906.02768/) (2019)
- [Discovering Evolution Strategies via Meta-Black-Box Optimization](https://mlsanity.com/paper/2211.11260/) (2022)
- [Discovering Attention-Based Genetic Algorithms via Meta-Black-Box Optimization](https://mlsanity.com/paper/2304.03995/) (2023)
- [A topological insight into restricted Boltzmann machines](https://mlsanity.com/paper/1604.05978/) (2016)
- [EvoJAX: Hardware-Accelerated Neuroevolution](https://mlsanity.com/paper/2202.05008/) (2022)
- [Winning Lottery Tickets in Deep Generative Models](https://mlsanity.com/paper/2010.02350/) (2020)
- [On Lottery Tickets and Minimal Task Representations in Deep Reinforcement Learning](https://mlsanity.com/paper/2105.01648/) (2021)
- [Towards Understanding Iterative Magnitude Pruning: Why Lottery Tickets Win](https://mlsanity.com/paper/2106.06955/) (2021)
- [Effective Mutation Rate Adaptation through Group Elite Selection](https://mlsanity.com/paper/2204.04817/) (2022)

## Built on by (most cited first, 2 of 2)

- [Searching Search Spaces: Meta-evolving a Geometric Encoding for Neural Networks](https://mlsanity.com/paper/2403.14019/) (2024)
- [Genetic Drift Regularization: on preventing Actor Injection from breaking Evolution Strategies](https://mlsanity.com/paper/2405.04322/) (2024)

## Abstract (arXiv)

Is the lottery ticket phenomenon an idiosyncrasy of gradient-based training or does it generalize to evolutionary optimization? In this paper we establish the existence of highly sparse trainable initializations for evolution strategies (ES) and characterize qualitative differences compared to gradient descent (GD)-based sparse training. We introduce a novel signal-to-noise iterative pruning procedure, which incorporates loss curvature information into the network pruning step. This can enable the discovery of even sparser trainable network initializations when using black-box evolution as compared to GD-based optimization. Furthermore, we find that these initializations encode an inductive bias, which transfers across different ES, related tasks and even to GD-based training. Finally, we compare the local optima resulting from the different optimization paradigms and sparsity levels. In contrast to GD, ES explore diverse and flat local optima and do not preserve linear mode connectivity across sparsity levels and independent runs. The results highlight qualitative differences between evolution and gradient-based learning dynamics, which can be uncovered by the study of iterative pruning procedures.