Research map / Optimization / Implicit bias and generalization
The Implicit Bias for Adaptive Optimization Algorithms on Homogeneous Neural Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use an exponential moving average conditioner instead of AdaGrad's cumulative squared-gradient conditioner | Adaptive optimization of homogeneous neural networks · MNIST | normalized margin | Helped |
| Use an exponential moving average conditioner instead of AdaGrad's cumulative squared-gradient conditioner | Adaptive optimization of homogeneous neural networks · MNIST | test accuracy | Helped |
| Use AdaGrad's cumulative squared-gradient conditioner | Adaptive optimization of homogeneous neural networks · MNIST, different initializations | convergent-direction stability | Hurt |
| Use Adam with momentum acceleration rather than Adam (w/m) | Adam · MNIST | normalized margin | No clear effect |
Closest papers by meaning
- Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks (ICLR 2025 · similarity 0.90)
- Implicit Bias of Gradient Descent for Non-Homogeneous Deep Networks (ICML 2025 · similarity 0.90)
- Non-asymptotic Analysis of Biased Adaptive Stochastic Approximation (NeurIPS 2024 · similarity 0.90)
- The Rich and the Simple: On the Implicit Bias of Adam and SGD (NeurIPS 2025 · similarity 0.89)
- Exact, Tractable Gauss-Newton Optimization in Deep Reversible Architectures Reveal Poor Generalization (NeurIPS 2024 · similarity 0.88)
- Adaptive Methods through the Lens of SDEs: Theoretical Insights on the Role of Noise (ICLR 2025 · similarity 0.88)
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.