Xinbing Kong, Zeyu Li, Junfan Mao, Bin Wu
arXiv 22 Sep 2026 · Statistics — Machine Learning
arXiv:2609.25924 · PDF · Extracted main text
Causal inference guides operational and managerial decisions but remains challenging in high-dimensional panel or tensor settings, where decisions may depend on the joint conditional distribution of missing control outcomes. We develop Counterfactual Tucker Diffusion (\CFTDiff), which integrates the treatment mask and latent Tucker structure into conditional diffusion to recover this distribution given observed control outcomes through efficient nonlinear score learning in a low-dimensional core. The masked Tucker score preserves dependence across tensor modes while reducing the dimension of nonlinear score learning from the product of mode dimensions to the much smaller product of Tucker ranks. We establish high-probability error bounds for conditional score estimation that depend on the Tucker ranks, largest mode dimension, and the factor-strength-adjusted number of missing outcomes, and show how these bounds translate into recovery guaranties for the conditional distribution of the missing control outcomes. Across missing rates, simulations show more accurate point recovery than common causal panel and matrix/tensor completion methods; comparisons with nested diffusion specifications further demonstrate the gains from masked conditioning and Tucker dimension reduction. In Norway's iFlex experiment, \CFTDiff recovers missing outcomes more accurately than competing methods; when applied to causal analysis, its estimated conditional distributions yield counterfactual prediction intervals and target-attainment probabilities, allowing pricing interventions to be evaluated by demand-reduction magnitude and reliability.
appendix boundary found by none_found · 100% 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 | Fu, Hengyu and Yang, Zhuoran and Wang, Mengdi and Chen, Minshuo (2024) Unveil conditional diffusion models with classifier-free guidance: A sharp statistical theory | 1.000 | 6 | 4 | 100% |
| 2 | Chen, Minshuo and Huang, Kaixuan and Zhao, Tuo and Wang, Mengdi (2023) Score approximation, estimation and distribution recovery of diffusion models on low-dimensional data | 0.928 | 4 | 3 | 100% |
| 3 | Ho, Jonathan and Jain, Ajay and Abbeel, Pieter (2020) Denoising diffusion probabilistic models | 0.928 | 4 | 3 | 100% |
| 4 | Hofmann, Matthias and Lindberg, Karen Byskov (2024) Evidence of Households' Demand Flexibility in Response to Variable Hourly Electricity Prices–-Results from a Comprehensive Field… | 0.874 | 5 | 2 | 100% |
| 5 | Guo, Jianhua and Kong, Xinbing and Li, Zeyu and Mao, Junfan (2026) Tucker Diffusion Model for High-dimensional Tensor Generation self | 0.811 | 4 | 2 | 100% |
| 6 | Song, Yang and Sohl-Dickstein, Jascha and Kingma, Diederik P and Kum… (2021) Score-based generative modeling through stochastic differential equations | 0.811 | 4 | 2 | 100% |
| 7 | Csiszár, Imre (1967) Information-Type Measures of Difference of Probability Distributions and Indirect Observations | 0.737 | 3 | 2 | 100% |
| 8 | Arkhangelsky, Dmitry and Athey, Susan and Hirshberg, David A and Imb… (2021) Synthetic difference-in-differences | 0.644 | 2 | 2 | 100% |
| 9 | Athey, Susan and Bayati, Mohsen and Doudchenko, Nikolay and Imbens,… (2021) Matrix completion methods for causal panel data models | 0.644 | 2 | 2 | 100% |
| 10 | Bakry, Dominique and Gentil, Ivan and Ledoux, Michel and others (2014) Analysis and geometry of Markov diffusion operators | 0.644 | 2 | 2 | 100% |
Showing the top 10 of 62 scored citations.