Research map / Optimization / Optimizers
Langevin Dynamics with Continuous Tempering for Training Deep 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 CTLD instead of the compared optimizers | 3-layer LSTM · Wikipedia Hutter Prize 100MB | training perplexity | Helped |
| Use CTLD instead of the compared optimizers | 3-layer LSTM · Wikipedia Hutter Prize 100MB | test perplexity | Helped |
| Use CTLD instead of the compared methods | stacked denoising autoencoder · MNIST | mean square error | Helped |
| Increase the temperature range by increasing S (ablation) | CTLD · War and Peace | local-minimum quality | Helped |
| Vary metadynamics parameters w and σ within the tested range (ablation) | CTLD · War and Peace | model performance | No clear effect |
| Use CTLD instead of SGD-M | MNIST CNN · MNIST classification | computation time: 3.8471 -> 3.8868 | No clear effect |
Closest papers by meaning
- Temperature is All You Need for Generalization in Langevin Dynamics and other Markov Processes (NeurIPS 2025 · similarity 0.89)
- Microcanonical Langevin Ensembles: Advancing the Sampling of Bayesian Neural Networks (ICLR 2025 · similarity 0.88)
- Provable Convergence and Limitations of Geometric Tempering for Langevin Dynamics (ICLR 2025 · similarity 0.88)
- Parameter Expanded Stochastic Gradient Markov Chain Monte Carlo (ICLR 2025 · similarity 0.87)
- A Study of Bayesian Neural Network Surrogates for Bayesian Optimization (ICLR 2024 · similarity 0.87)
- Sample as you Infer: Predictive Coding with Langevin Dynamics (ICML 2024 · similarity 0.87)
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.