Research map / Probabilistic and scientific modeling / Variational and generative sampling
Dimensionally Tight Bounds for Second-Order Hamiltonian Monte Carlo
Oren Mangoubi, Nisheeth Vishnoi
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 |
|---|---|---|---|
| Use the infinity-norm Lipschitz condition on Hessian changes in data-associated directions instead of relying only on a Euclidean Lipschitz Hessian bound | Second-order unadjusted HMC with leapfrog · Strongly log-concave targets, warm start | gradient evaluations: O^{*}(d^{\frac{1}{2}}) -> O^{*}(d^{\frac{1}{4}}) | Improved |
| Use the new regularity condition when it holds | Leapfrog HMC · Synthetic data simulations | accuracy | Improved |
| Use unadjusted leapfrog HMC without a Metropolis filter | Bayesian logistic regression on synthetic data · Synthetic data | accuracy | Mixed |
Closest papers by meaning
- On the Convergence of Hamiltonian Monte Carlo with Stochastic Gradients (ICML 2021 · similarity 0.92)
- Non-asymptotic Error Bounds in $\mathcal{W}_2$-Distance with Sqrt(d) Dimension Dependence and First Order Convergence for Langevin Monte Carlo beyond Log-Concavity (ICML 2025 · similarity 0.88)
- Constrained Sampling with Primal-Dual Langevin Monte Carlo (NeurIPS 2024 · similarity 0.87)
- Hamiltonian Monte Carlo on ReLU Neural Networks is Inefficient (NeurIPS 2024 · similarity 0.86)
- Metropolis Adjusted Microcanonical Hamiltonian Monte Carlo (NeurIPS 2025 · similarity 0.86)
- Langevin Monte Carlo for strongly log-concave distributions: Randomized midpoint revisited (ICLR 2024 · similarity 0.86)
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.
