Research map / Optimization / Nonconvex and smooth optimization
Learning Infinite RBMs with Frank-Wolfe
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 |
|---|---|---|---|
| Initialize CD from the Frank-Wolfe-learned model instead of random initialization | RBM trained with CD · MNIST and Caltech101 Silhouettes | test log-likelihood | Helped |
| Use Frank-Wolfe with early stopping to choose the number of hidden units | Infinite RBM / FW · MNIST and Caltech101 Silhouettes | test log-likelihood | Helped |
| Train FW-initialized CD versus best of 5 random CD initializations for classification features | CD initialized by FW · MNIST and Caltech101 classification | classification error | Helped |
| Basic FW features versus fully trained CD features when few hidden units are added | Frank-Wolfe RBM · MNIST and Caltech101 classification | classification error | Mixed |
Closest papers by meaning
- Learning with Restricted Boltzmann Machines: Asymptotics of AMP and GD in High Dimensions (NeurIPS 2025 · similarity 0.90)
- Fast training and sampling of Restricted Boltzmann Machines (ICLR 2025 · similarity 0.88)
- Sarah Frank-Wolfe: Methods for Constrained Optimization with Best Rates and Practical Features (ICML 2024 · similarity 0.86)
- BoltzNCE: Learning likelihoods for Boltzmann Generation with Stochastic Interpolants and Noise Contrastive Estimation (NeurIPS 2025 · similarity 0.84)
- Spherical Boltzmann machines: a solvable theory of learning and generation in energy-based models (NeurIPS 2026 · similarity 0.84)
- Cascade of phase transitions in the training of energy-based models (NeurIPS 2024 · 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.