Institution profile

University of Cambridge

Academic institutioneurope · gb
Official website
Research library2,278linked papers
Opportunities0open roles
Selected work

Representative Papers

How to Detect Network Dependence in Latent Factor Models? A Bias-Corrected CD Test

Sep 01, 2021

This paper addresses the failure of residual cross-sectional dependence tests in latent factor panel models. We propose a bias-corrected CD* test statistic. Theoretically, we first establish the asymptotic validity of the standard CD test under weak factors and rigorously derive the asymptotic standard normality of CD* under the null hypothesis, while demonstrating its high local power against network-type alternatives. Methodologically, the CD* test integrates factor estimation, residual extraction, and analytical bias correction, accommodating both strong and weak factors as well as serially correlated errors. Monte Carlo simulations show that CD* achieves accurate size and superior power in small samples, consistently outperforming the JR test. Empirically, applying CD* to a housing price dynamics model across 377 U.S. metropolitan statistical areas reveals statistically significant spatial dependence in residuals.

49 citations1 influentialRead paper

FedConv: A Learning-on-Model Paradigm for Heterogeneous Federated Clients

Jun 03, 2024ACM SIGMOBILE International Conference on Mobile Systems, Applications, and Services

To address the uneven computational burden imposed by client-side resource heterogeneity in federated learning (FL), this paper proposes FedConv. It trains lightweight submodels directly in compressed convolutional form, eliminating decompression overhead. FedConv introduces the novel “learning-on-model” paradigm—the first approach enabling end-to-end training of compressed submodels. It further designs a transposed-convolution-based expansion mechanism to unify aggregation of heterogeneous submodels while preserving personalized parameters. Complemented by joint optimization on the server using a small public dataset, FedConv achieves an average accuracy improvement of 35.2% across six benchmark datasets, while reducing computational cost by 33.1% and communication cost by 24.8%, significantly outperforming existing FL methods.

7 citationsRead paper

Reuniting χ-boundedness with polynomial χ-boundedness

Oct 17, 2023arXiv.org

This paper investigates the structural relationship between χ-boundedness and polynomial χ-boundedness by introducing and systematically studying “Pollyanna graph classes”—graph classes whose intersection with any χ-bounded class remains polynomially χ-bounded. Method: Employing combinatorial graph theory, induced-subgraph coloring analysis, and asymptotic growth-rate comparison, the authors develop a necessary and sufficient condition framework for Pollyanna property. Contribution/Results: They prove that several fundamental graph classes—including perfect graphs and chordal graphs—are Pollyanna; moreover, they construct the first explicit non-Pollyanna graph class, establishing the nontriviality of the property. These results provide a novel classification tool and decision paradigm for χ-boundedness theory, enriching its structural foundations and offering new criteria for distinguishing polynomial from general χ-bounded behavior.

4 citations2 influentialRead paper

Supply Chain Disruptions, the Structure of Production Networks, and the Impact of Globalization

Nov 05, 2025Social Science Research Network

This paper investigates how supply chain disruptions propagate across goods and final consumers in multi-sector international production networks, focusing on how node positions and network structural features shape systemic vulnerability. We develop a parsimonious model integrating production network theory with multi-sector general equilibrium, employing analytical derivation and comparative statics. Our results show: (1) Disruption shocks exhibit a “sharp short-term, decaying long-term” dynamic; (2) Node centrality and network complexity significantly amplify global welfare losses from localized disruptions; (3) Declining transport costs reduce disruption frequency but reinforce specialization, thereby exacerbating negative spillovers from single-node failures; (4) Countries can acquire asymmetric economic influence through control over production and strategic trade quotas. The study provides a structured theoretical benchmark for assessing globalization-related risks and designing supply chain resilience policies.

4 citations1 influentialRead paper

Root Cause Analysis of Outliers with Missing Structural Knowledge

Jun 07, 2024arXiv.org

Real-world root cause analysis (RCA) faces a critical challenge: post-intervention distributions often contain only a few—or even a single—sample, rendering distribution-dependent or low-density-region regression methods statistically ill-posed. This paper proposes a lightweight root cause identification framework that requires neither counterfactual reasoning nor a fully specified structural causal model (SCM). It operates either given a causal DAG or, in the absence of one, solely from an anomaly score ranking. We theoretically prove that low-scoring anomalies rarely trigger high-scoring ones and derive a probabilistic upper bound on non-monotonic propagation paths. By abandoning Shapley-value-based attribution and density-sensitive regression, our method achieves linear time complexity O(n). It eliminates SCM fitting and counterfactual computation while providing rigorous theoretical guarantees and strong empirical performance.

4 citations1 influentialRead paper
Recent publications

Latest Papers