Beyond Pretrends: A Discordance-Based Sensitivity Analysis for Difference-in-Differences
本文针对差异中的差异设计中由于组间差异导致的混淆问题，提出了一种基于不一致性的敏感性分析方法，以评估平行趋势假设下的因果结论稳健性。
0 citationsRead paper
Selected work
Representative Papers
Hyperbolic Latent Position Models for Hierarchical Bipartite Data
This study addresses the challenge of jointly modeling bipartite data heterogeneity and hierarchical interactions by proposing HELPI. The method embeds dyadic objects into hyperbolic space to disentangle geometric interactions from additive biases, utilizing root-invariant projections to identify hierarchical structures and augmented variational inference for efficient posterior computation. Theoretically, we establish the likelihood equivalence between hyperbolic distances and root Gromov product predictors, alongside posterior contraction properties. Empirical results demonstrate that HELPI accurately recovers hierarchical structures and yields interpretable geometric representations on educational and voting datasets. The model outperforms existing baselines in predictive performance and successfully uncovers latent partisan and policy structures without supervision, validating its effectiveness in capturing complex relational patterns within heterogeneous bipartite data.
0 citationsRead paper
Learning Nearest-Neighbor Maps from Adaptive Queries
This work investigates the optimal query complexity for reconstructing a hidden point set via adaptive nearest neighbor queries in arbitrary normed spaces. It introduces a novel approach integrating geometric analysis, adaptive querying strategies, randomized dimensionality reduction, and kissing number theory, establishing—for the first time—the tight worst-case query complexity bound of Θ(nκ) under general norms. A key insight is the fundamental distinction between spherical and ball-shaped query domains: while reconstruction within a Euclidean ball admits complexity O(min(n,d)), exponential queries are necessary for balls and cones in general norms. The study also refines dimensionality reduction techniques on spheres, underscoring how intrinsic geometric structure critically governs the difficulty of learning.
0 citationsRead paper
Two-Stage Bengali Sentiment Classification: Domain Adaptation Through Continual Learning and Parameter-Efficient Fine-Tuning
This work addresses the challenge of sentiment classification for low-resource languages like Bengali under domain data scarcity by proposing SentiBanglaBERT, a novel framework employing a two-stage strategy. First, it enhances contextual adaptability through continued pretraining on news-domain corpora; second, it leverages Low-Rank Adaptation (LoRA) for parameter-efficient fine-tuning. The approach innovatively integrates domain adaptation with interpretability analysis, utilizing SHAP to uncover the influence of key Bengali morphological features—such as negation suffixes and aspect markers—on sentiment predictions. Experimental results demonstrate that the model achieves performance comparable to strong baselines while maintaining computational efficiency and offering linguistically insightful explanations.
0 citationsRead paper
Heat-Kernel Entropy Profiles and Geometric Effective Sample Size for Weighted Measures on Manifolds
This work addresses the limitation of traditional effective sample size (ESS) estimators, which disregard the geometric structure of the underlying support manifold and thus fail to capture the distributional characteristics of weighted measures in complex spaces. The authors propose a geometrically aware ESS metric—termed the heat kernel entropy profile—that uniquely integrates the heat kernel with Rényi entropy. By diffusing weighted atoms via intrinsic heat flow, the method tracks multiscale non-uniformities, preserving classical ESS properties while detecting proximate or redundant particles and intricate spherical structures. The approach combines heat kernel overlap computation, spherical harmonic decomposition, and self-normalized importance sampling, and establishes asymptotic theory on compact boundaryless manifolds. Theoretical analysis confirms its monotonicity, consistency, and asymptotic behavior, while spherical experiments successfully reveal geometric features—such as antipodal points, zonal bands, and multimodal configurations—that conventional methods overlook.
0 citationsRead paper
Recent publications
Latest Papers
Beyond Pretrends: A Discordance-Based Sensitivity Analysis for Difference-in-Differences
本文针对差异中的差异设计中由于组间差异导致的混淆问题，提出了一种基于不一致性的敏感性分析方法，以评估平行趋势假设下的因果结论稳健性。
0 citationsRead paper
Hyperbolic Latent Position Models for Hierarchical Bipartite Data
This study addresses the challenge of jointly modeling bipartite data heterogeneity and hierarchical interactions by proposing HELPI. The method embeds dyadic objects into hyperbolic space to disentangle geometric interactions from additive biases, utilizing root-invariant projections to identify hierarchical structures and augmented variational inference for efficient posterior computation. Theoretically, we establish the likelihood equivalence between hyperbolic distances and root Gromov product predictors, alongside posterior contraction properties. Empirical results demonstrate that HELPI accurately recovers hierarchical structures and yields interpretable geometric representations on educational and voting datasets. The model outperforms existing baselines in predictive performance and successfully uncovers latent partisan and policy structures without supervision, validating its effectiveness in capturing complex relational patterns within heterogeneous bipartite data.
0 citationsRead paper
Learning Nearest-Neighbor Maps from Adaptive Queries
This work investigates the optimal query complexity for reconstructing a hidden point set via adaptive nearest neighbor queries in arbitrary normed spaces. It introduces a novel approach integrating geometric analysis, adaptive querying strategies, randomized dimensionality reduction, and kissing number theory, establishing—for the first time—the tight worst-case query complexity bound of Θ(nκ) under general norms. A key insight is the fundamental distinction between spherical and ball-shaped query domains: while reconstruction within a Euclidean ball admits complexity O(min(n,d)), exponential queries are necessary for balls and cones in general norms. The study also refines dimensionality reduction techniques on spheres, underscoring how intrinsic geometric structure critically governs the difficulty of learning.
0 citationsRead paper
Two-Stage Bengali Sentiment Classification: Domain Adaptation Through Continual Learning and Parameter-Efficient Fine-Tuning
This work addresses the challenge of sentiment classification for low-resource languages like Bengali under domain data scarcity by proposing SentiBanglaBERT, a novel framework employing a two-stage strategy. First, it enhances contextual adaptability through continued pretraining on news-domain corpora; second, it leverages Low-Rank Adaptation (LoRA) for parameter-efficient fine-tuning. The approach innovatively integrates domain adaptation with interpretability analysis, utilizing SHAP to uncover the influence of key Bengali morphological features—such as negation suffixes and aspect markers—on sentiment predictions. Experimental results demonstrate that the model achieves performance comparable to strong baselines while maintaining computational efficiency and offering linguistically insightful explanations.
0 citationsRead paper
Heat-Kernel Entropy Profiles and Geometric Effective Sample Size for Weighted Measures on Manifolds
This work addresses the limitation of traditional effective sample size (ESS) estimators, which disregard the geometric structure of the underlying support manifold and thus fail to capture the distributional characteristics of weighted measures in complex spaces. The authors propose a geometrically aware ESS metric—termed the heat kernel entropy profile—that uniquely integrates the heat kernel with Rényi entropy. By diffusing weighted atoms via intrinsic heat flow, the method tracks multiscale non-uniformities, preserving classical ESS properties while detecting proximate or redundant particles and intricate spherical structures. The approach combines heat kernel overlap computation, spherical harmonic decomposition, and self-normalized importance sampling, and establishes asymptotic theory on compact boundaryless manifolds. Theoretical analysis confirms its monotonicity, consistency, and asymptotic behavior, while spherical experiments successfully reveal geometric features—such as antipodal points, zonal bands, and multimodal configurations—that conventional methods overlook.
0 citationsRead paper