Research map / Optimization / Implicit bias and generalization
Symmetry Teleportation for Accelerated Optimization
Bo Zhao, Nima Dehmamy, Robin Walters, Rose Yu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add symmetry teleportation to gradient descent | Gradient descent · Rosenbrock function | steps to reach target | Improved |
| add symmetry teleportation to gradient descent | Gradient descent · Booth function | convergence rate | Improved |
| add teleportation to GD and AdaGrad | GD, AdaGrad · 3-layer network regression | epochs and time to convergence | Improved |
| add teleportation to SGD | SGD · MNIST | training loss | Improved |
| add teleportation to AdaGrad | AdaGrad · MNIST | validation loss | Hurt |
| add teleportation | SGD · MNIST | validation accuracy | Hurt |
| teleport before training instead of after epoch 0 (ablation) | SGD with teleportation · MNIST | training loss | Hurt |
| teleport earlier (after epoch 0) (ablation) | SGD with teleportation · MNIST | training loss | Improved |
| smaller intervals between teleportations (ablation) | SGD with teleportation · MNIST | convergence speed | Improved |
| teleport using more mini-batches (ablation) | SGD with teleportation · MNIST | training loss | Improved |
Closest papers by meaning
- Improving Convergence and Generalization Using Parameter Symmetries (ICLR 2024 · similarity 0.96)
- Continual Optimization with Symmetry Teleportation for Multi-Task Learning (NeurIPS 2025 · similarity 0.89)
- Scalable Decentralized Learning with Teleportation (ICLR 2025 · similarity 0.85)
- Fast T2T: Optimization Consistency Speeds Up Diffusion-Based Training-to-Testing Solving for Combinatorial Optimization (NeurIPS 2024 · similarity 0.84)
- Adaptively Incorporating Directional Hints into Zeroth-Order Optimization (NeurIPS 2026 · similarity 0.84)
- Incremental Gradient Descent with Small Epoch Counts is Surprisingly Slow on Ill-Conditioned Problems (ICML 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
