Paper ID: 2411.04658
Finding Strong Lottery Ticket Networks with Genetic Algorithms
Philipp Altmann, Julian Schönberger, Maximilian Zorn, Thomas Gabor
According to the Strong Lottery Ticket Hypothesis, every sufficiently large neural network with randomly initialized weights contains a sub-network which - still with its random weights - already performs as well for a given task as the trained super-network. We present the first approach based on a genetic algorithm to find such strong lottery ticket sub-networks without training or otherwise computing any gradient. We show that, for smaller instances of binary classification tasks, our evolutionary approach even produces smaller and better-performing lottery ticket networks than the state-of-the-art approach using gradient information.
Submitted: Nov 7, 2024