Research map / Learning theory and algorithms / Sample complexity
How good is your Laplace approximation of the Bayesian posterior? Finite-sample computable error bounds for a variety of useful divergences
Mikolaj J. Kasprzak, Ryan Giordano, Tamara Broderick
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 computable Laplace bounds on posterior mean and variance difference for Poisson likelihood with gamma prior under exponential data (misspecified) | MAP-centric Laplace bound · Poisson-gamma, exponential data with mean 10 | bound vs true difference of means and variances: close to true difference for sample sizes above around 250 | Improved |
| smaller condition number of the Hessian matrix (ablation) | Laplace error bound · logistic regression with Student's t prior | bound tightness | No clear effect |
| small or moderate sample size (ablation) | Laplace error bound · numerical examples | bound tightness | Hurt |
Closest papers by meaning
- General bounds on the quality of Bayesian coresets (NeurIPS 2024 · similarity 0.87)
- Asymptotic Consistency of $\alpha$-{R}ényi-Approximate Posteriors (JMLR 2020 · similarity 0.85)
- FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning (NeurIPS 2024 · similarity 0.84)
- 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 0.84)
- Asymptotically Log-Optimal Bayes-Assisted Confidence Sequences for Bounded Means (NeurIPS 2026 · similarity 0.83)
- Bounds on $L_p$ Errors in Density Ratio Estimation via $f$-Divergence Loss Functions (ICLR 2025 · similarity 0.83)
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.
