Institution profile

Bocconi University

Academic institutioneurope · it
Official website
Research library192linked papers
Opportunities0open roles
Selected work

Representative Papers

Skew-symmetric approximations of posterior distributions

Sep 21, 2024

Bayesian posteriors are often skewed, whereas mainstream deterministic approximations—such as Laplace’s method and variational Bayes—rely on symmetric densities (e.g., Gaussians), leading to systematic bias and reduced accuracy. Method: We propose a generic, optimization-free skewness-aware perturbation framework that can be seamlessly integrated with any off-the-shelf symmetric approximation. Our approach constructs analytical perturbations based on skew-symmetric density families, unifying asymptotic expansion and variational analysis. Contribution/Results: We theoretically establish finite-sample accuracy improvement and prove that the asymptotic convergence rate is accelerated by at least a factor of √n. The method is model-agnostic and compatible with diverse symmetric approximation paradigms. Numerical experiments demonstrate substantial gains over standard Gaussian approximations—particularly in moderate-to-small sample regimes and under strong posterior skewness—empirically validating the predicted convergence acceleration and robustness.

2 citations1 influentialRead paper

Multivariate Species Sampling Models

Mar 31, 2025

Existing nonparametric prior models lack a unified framework, leaving their clustering structures and information-sharing mechanisms poorly understood. Method: We propose the Multivariate Species Sampling (MVSS) model—the first systematic, general framework unifying mainstream finite- and infinite-dimensional dependent discrete processes. Grounded in partial exchangeability theory, MVSS characterizes multivariate dependence via random partition probability functions. We further introduce the regular MVSS subclass, whose inter-process dependence is continuously controlled by a correlation coefficient (ranging from 0 for independence to 1 for full exchangeability). Contribution/Results: MVSS provides an interpretable, tunable modeling foundation for partially exchangeable data, revealing underlying distributional mechanisms. It substantially extends the theoretical boundaries and design flexibility of Bayesian nonparametric modeling, enabling principled construction and analysis of dependent discrete processes.

1 citationsRead paper

The Division of Surplus and the Burden of Proof

Jan 24, 2025

This paper examines residual value allocation and evidentiary burden assignment within a principal–agent framework: the agent privately observes the residual magnitude and chooses an initial disclosure; both parties incur costly effort to acquire hard evidence, and the agent’s liability is capped at the disclosed value. The principal commits to her own effort level and designs the allocation rule based on evidence ownership. The study is the first to endogenize evidentiary costs, disclosure constraints, and liability caps into optimal mechanism design. It derives closed-form solutions for both parties’ evidentiary efforts and reveals that the agent’s effort exhibits a non-monotonic, five-region pattern in response to the disclosure level. The results characterize the fundamental trade-off between residual allocation efficiency and evidentiary incentives, providing theoretical foundations for wealth taxation, corporate finance, and public procurement.

1 citationsRead paper
Recent publications

Latest Papers

Structuring the Space of Perspectives

Aug 12, 2026

This study addresses the conceptual ambiguity and unclear interrelationships among stance, sentiment, framing, and argumentation—key perspective-related constructs in natural language processing—that stem from the absence of a unified theoretical framework. Through a systematic literature review and conceptual analysis, the work proposes a set of distinguishing attributes and, for the first time, formulates a linear hierarchical model that clarifies the intrinsic logical relationships among these constructs. The resulting model offers a coherent theoretical foundation and a conceptual navigation tool for perspective research, enabling scholars to select appropriate operationalization pathways aligned with their specific task objectives. This advancement enhances the systematicity and effectiveness of research on linguistic perspectives.

0 citationsRead paper

A Subsampling Theorem for Constraint Satisfaction Problems with Large Arity

Jul 31, 2026

This study addresses the problem of efficiently subsampling high-arity constraint satisfaction problems (CSPs) while preserving their optimal value up to a small approximation error. The authors propose a randomized subsampling method that selects only a small subset of variables yet accurately approximates the optimum of the original CSP. This work establishes the first subsampling theorem for CSPs of arbitrary arity $k$, achieving sample complexity polynomial in $k$ and the error parameter $\varepsilon$, and polylogarithmic in the alphabet size $q$. By integrating techniques from probabilistic analysis, property testing, and computational complexity theory, the approach not only provides a crucial ingredient in proving $\mathrm{AM}(\mathrm{poly}) = \mathrm{AM}$, but also yields the first one-sided CSP satisfiability tester with significantly improved sample complexity over prior results.

0 citationsRead paper