Jun-ya Gotoh, Andrew E. B. Lim, Michael Jong Kim
arXiv 29 May 2026 · Mathematics — Optimization
arXiv:2605.31306 · PDF · DOI · OpenAlex · Extracted main text
We introduce the notion of worst-case posterior and worst-case likelihood sensitivity. These measure, respectively, the sensitivity of the expected cost to worst-case perturbations of the posterior distribution and worst-case perturbations of the likelihood of a Bayesian model. Each defines a quantitative measure of robustness. A decision maker concerned about the sensitivity of the out-of-sample expected cost to deviations from her assumptions will want a decision for which both sensitivities are small. We derive posterior and likelihood sensitivities for uncertainty sets defined in terms of deviation measures. Posterior sensitivity vanishes when the posterior variance shrinks to zero, which occurs when parameter uncertainty is eliminated from learning. Parameter learning does not eliminate likelihood sensitivity. A distributionally robust formulation of a Bayesian optimization problem makes a near-Pareto-optimal tradeoff between performance (expected cost) and robustness (posterior and likelihood sensitivity).
appendix boundary found by appendix_command · 85% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Gotoh, Jun-ya and Kim, Michael Jong and Lim, Andrew E.B (2026) Robustness Measures in Distributionally Robust Optimization self | 1.000 | 12 | 4 | 100% |
| 2 | Shapiro, Alexander and Zhou, Enlu and Lin, Yifan (2023) Bayesian distributionally robust optimization | 0.644 | 2 | 2 | 100% |
| 3 | Duchi, John C. and Namkoong, Hongseok (2019) Variance-based regularization with convex objectives | 0.405 | 1 | 1 | 100% |
| 4 | Lavine, Michael (1991) Sensitivity in Bayesian Statistics: The Prior and the Likelihood | 0.405 | 1 | 1 | 100% |
| 5 | Berger, James and Berliner, L. Mark (1986) ROBUST BAYES AND EMPIRICAL BAYES ANALYSIS WITH $ $-CONTAMINATED PRIORS | 0.405 | 1 | 1 | 100% |
| 6 | Bertsimas, Dimitris and Copenhaver, Martin S (2018) Characterization of the equivalence of robustification and regularization in linear and matrix regression | 0.405 | 1 | 1 | 100% |
| 7 | Blanchet, Jose and Kang, Yang and Murthy, Karthyek (2019) Robust Wasserstein profile inference and applications to machine learning | 0.405 | 1 | 1 | 100% |
| 8 | Esfahani, Peyman Mohajerin and Kuhn, Daniel (2018) Data-driven distributionally robust optimization using the Wasserstein metric: Performance guarantees and tractable reformulations | 0.405 | 1 | 1 | 100% |
| 9 | Gao, Rui and Kleywegt, Anton (2023) Distributionally robust stochastic optimization with Wasserstein distance | 0.405 | 1 | 1 | 100% |
| 10 | Gao, Rui and Chen, Xi and Kleywegt, Anton J (2024) Wasserstein distributionally robust optimization and variation regularization | 0.405 | 1 | 1 | 100% |
Showing the top 10 of 15 scored citations.