Publications

Topic All Causal Inference Network Interference Meta-Learner Survey Sampling Bandits & RL Permutation High-Dimensional NLP / LLM Collaborative Design-based Inference
Venue All Preprint ML Conference Journal
Sort Year ↓ Newest Year ↑ Oldest
Lu, S., Shi, L. and Ding, P. (2026) Estimating within-cluster and between-cluster spillover effects in randomized saturation designs. Social Networks, 87, 24–34. [Slides]
Shi, L., Zhang, A., Lyu, R., Hu, Z., Yu, T., Arbour, D., Feller, A., Mitra, S. and Sinha, R. (2026) BACON: Budgeted Human Calibration for Modeling and Evaluation with Multiple AI Judges.
Hu, Z., Shi, L., Sinha, R., Grover, J. and Arbour, D. (2026) Experimentation Accelerator: Interpretable Insights and Creative Recommendations for A/B Testing with Content-Aware ranking. KDD 2026.
Qi, S., Huang, C., Yu, T., Shi, L., Wu, J., McAuley, J. and Yao, L. (2026+) ColdSkill: Semantic-Graph Skill-Skill Expansion for Item-Side Cold-Start Routing in Agent Skills.
Hooda, R., Machcha, S., MacDonald, J., Srinivasaraghavan, L., Nijasure, A., Wang, R., Shi, L., Wu, J. and Yu, T. (2026) Multi-View Structural Interpretability of Agentic Reasoning Traces. EMNLP 2026, Industry Track. Accepted.
Lu, X., Shi, L., Liu, H. and Ding, P. (2025+) Conditional cross-fitting for unbiased machine-learning-assisted covariate adjustment in randomized experiments.
Shi, L., Lyu, Q. and Lu, S. (2025+) GAUGER: Generalized Regression Adjustment via GER for Design-Based Inference Under Interference.
Lu, S., Shi, L., Fang, Y., Zhang, W. and Ding, P. (2025+) Design-based causal inference in bipartite experiments. [Slides]
Shi, L., Lu, S., Lyu, Q., Ding, P. and Vlassis, N. (2025+) TERRA: A Transformer-Enabled Recursive R-learner for Longitudinal Heterogeneous Treatment Effect Estimation.
Shi, L., Arbour, D., Addanki, R., Sinha, R. and Feller, A. (2025+) Leveraging semantic similarity for experimentation with AI-generated treatments. NeurIPS 2025.
Lyu, Q., Wang, M. and Shi, L. (2025+) QUARK: Robust Retrieval under Non-Faithful Queries via Query-Anchored Aggregation.
Shi, L., Wang, J. and Ding, P. (2024) Forward selection and post-selection inference in factorial designs. Annals of Statistics. Accepted. [Slides]
Shi, L. and Li, X. (2024) Some theoretical foundations on the design and analysis of randomized experiments. Journal of Causal Inference. Accepted.
Shi, L. and Ding, P. (2024+) Asymptotic theory for the quadratic assignment procedure. [Slides]
Shi, L., Wei, W. and Wang, J. (2024+) Using Surrogates in Covariate-adjusted Response-adaptive Randomized Experiments with Delayed Outcomes. NeurIPS 2024. [Slides]
Shi, L., Wang, G. and Zou, C. (2024) Low-Rank Matrix Estimation in the Presence of Change-Points. Journal of Machine Learning Research. [Distinguished Student Paper Award Winner for ENAR 2023]
Barbehenn, A., Shi, L., Shao, J., Hoh, R., Hartig, H.M., Pae, V., Sarvadhavabhatla, S., Donaire, S., Sheikhzadeh, C., Milush, J., Laird, G.M., et al. (2024) Rapid Biphasic Decay of Intact and Defective HIV DNA Reservoir During Acute Treated HIV Disease. Nature Communications. Accepted.
Shi, L., Pang, H., Chen, C. and Zhu, J. (2024+) rdborrow: An R package for Causal Inference Incorporating External Controls in Randomized Trials with Longitudinal Outcomes. Journal of Biopharmaceutical Statistics. Accepted. [Slides]
Barbehenn, A., Shi, L., Shao, J., Hoh, R., Hartig, H.M., Pae, V., Sarvadhavabhatla, S., Donaire, S., Sheikhzadeh, C., Savur, S., Milush, J., Laird, G.M., et al. (2026) IL-10 and Coordinated Cytokine Responses Predict Rapid HIV Reservoir Decay in Acute Treated HIV Infection. medRxiv.
Shi, L., Wang, J. and Wu, T. (2023) Statistical inference on multi-armed bandits with delayed feedback. ICML 2023.
Cui, X., Shi, L., Zhong, W. and Zou, C. (2023) Robust high-dimensional low-rank matrix estimation: optimal rate and data-adaptive tuning. Journal of Machine Learning Research.
Shi, L., Yang, H. and Xue, L. (2023+) Oracle Inequalities for Sparse Principal Component Analysis based on the Linear Manifold Approximation.
Shi, L. and Ding, P. (2022+) Berry–Esseen bounds for design-based causal inference with possibly diverging treatment levels and varying group sizes. Annals of Statistics. Accepted. [Slides]
Shi, L. and Zou, C. (2020) Noisy Low Rank Matrix Completion Under General Bases. Stat.
Contextual Bandits with LLM-Derived Priors and Adaptive Calibration.