Research map / Optimization / Optimizers
Stochastic Quasi-Newton Langevin Monte Carlo
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 dense L-BFGS inverse-Hessian approximations with HAMCMC instead of SGLD's isotropic updates | HAMCMC · Linear Gaussian Model, D=10 and D=100 | squared posterior-mean estimation error | Helped |
| Use HAMCMC with M=3 instead of SGLD or PSGLD | Linear Gaussian Model, D=10 and D=100 · Linear Gaussian Model | squared posterior-mean estimation error | Helped |
| Use HAMCMC instead of SGRLD | Linear Gaussian Model, D=10 and D=100 · Linear Gaussian Model | squared posterior-mean estimation error versus wall-clock time | Mixed |
| Use HAMCMC instead of SGLD or PSGLD | Alpha-Stable Matrix Factorization · Speech enhancement, test set at mixture SNR 5dB | SDR | Helped |
| Use HAMCMC instead of DSGLD or distributed PSGLD | Distributed matrix factorization · MovieLens 1M test set | RMSE | Helped |
Closest papers by meaning
- Stochastic Gradient Richardson-Romberg Markov Chain Monte Carlo (NeurIPS 2016 · similarity 0.93)
- A Hybrid Stochastic Gradient Hamiltonian Monte Carlo Method (AAAI 2021 · similarity 0.92)
- Structured Stochastic Gradient MCMC (ICML 2022 · similarity 0.92)
- Stochastic Gradient Hamiltonian Monte Carlo Methods with Recursive Variance Reduction (NeurIPS 2019 · similarity 0.91)
- Langevin Quasi-Monte Carlo (NeurIPS 2023 · similarity 0.91)
- Accelerating Langevin Monte Carlo via Efficient Stochastic Runge-Kutta Methods beyond Log-Concavity (ICML 2026 · similarity 0.91)
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.