← Back to Explore

Winning the Lottery by Preserving Network Training Dynamics With Concrete Ticket Search

ISEF · 2026 Robotics and Intelligent Machines

Overview

The Lottery Ticket Hypothesis posits that highly sparse, trainable subnetworks ('winning tickets') exist within all randomly initialized neural networks. However, state-of-the-art ticket-drawing methods, like Lottery Ticket Rewinding (LTR), are computationally prohibitive, while more efficient saliency-based Pruning-at-Initialization (PaI) techniques suffer from a significant performances drops and fail basic sanity checks. In this work, we argue that PaI's reliance on first-order saliency metrics, which ignore inter-weight dependencies, contributes substantially to this performance gap. To address this, we introduce Concrete Ticket Search (CTS), which frames subnetwork discovery as holistic combinatorial optimization. By leveraging a Concrete relaxation of the discrete search space and a novel gradient balancing scheme (GRADBALANCE) to control sparsity, CTS efficiently identifies high-performing subnetworks near initialization without requiring sensitive hyperparameter tuning. Motivated by recent works on lottery ticket training dynamics, we further propose a knowledge distillation-inspired family of pruning objectives, finding that minimizing the reverse Kullback-Leibler divergence between sparse and dense network outputs (CTS-KL) is particularly effective. Experiments on varying baseline image tasks show that CTS produces subnetworks that robustly pass sanity checks and perform close to or better than LTR, while requiring only a small fraction of the computation. For example, on ResNet-20/CIFAR10 at 99.3% sparsity, it attains 74.0% accuracy in 7.9 minutes, while LTR achieves 68.3% accuracy in 95.2 minutes. CTS's subnetworks outperform saliency methods across all sparsities, but its accuracy advantage over LTR is most pronounced in the highly sparse regime.

Competition history

  • ISEF 2026 Robotics and Intelligent Machines · Entry ROBO057

Resources

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Source: Regeneron International Science and Engineering Fair

Save projects to your library

Sign in with Google to keep track of projects you find interesting, organized into folders. Browsing stays public.

Continue with Google