Near-Efficient and Non-Asymptotic Multiway Inference
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908636133982208 |
|---|---|
| author | López, Oscar Prasadan, Arvind Llosa-Vite, Carlos Lehoucq, Richard B. Dunlavy, Daniel M. |
| author_facet | López, Oscar Prasadan, Arvind Llosa-Vite, Carlos Lehoucq, Richard B. Dunlavy, Daniel M. |
| contents | We establish non-asymptotic efficiency guarantees for tensor decomposition-based inference in count data models. Under a Poisson framework, we consider two related goals: (i) parametric inference, the estimation of the full distributional parameter tensor, and (ii) multiway analysis, the recovery of its canonical polyadic (CP) decomposition factors. Our main result shows that in the rank-one setting, a rank-constrained maximum-likelihood estimator achieves multiway analysis with variance matching the Cramér-Rao Lower Bound (CRLB) up to absolute constants and logarithmic factors. This provides a general framework for studying "near-efficient" multiway estimators in finite-sample settings. For higher ranks, we illustrate that our multiway estimator may not attain the CRLB; nevertheless, CP-based parametric inference remains nearly minimax optimal, with error bounds that improve on prior work by offering more favorable dependence on the CP rank. Numerical experiments corroborate near-efficiency in the rank-one case and highlight the efficiency gap in higher-rank scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_05368 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Near-Efficient and Non-Asymptotic Multiway Inference López, Oscar Prasadan, Arvind Llosa-Vite, Carlos Lehoucq, Richard B. Dunlavy, Daniel M. Statistics Theory Numerical Analysis Machine Learning 62F99 (Primary) 15A69 (Secondary) We establish non-asymptotic efficiency guarantees for tensor decomposition-based inference in count data models. Under a Poisson framework, we consider two related goals: (i) parametric inference, the estimation of the full distributional parameter tensor, and (ii) multiway analysis, the recovery of its canonical polyadic (CP) decomposition factors. Our main result shows that in the rank-one setting, a rank-constrained maximum-likelihood estimator achieves multiway analysis with variance matching the Cramér-Rao Lower Bound (CRLB) up to absolute constants and logarithmic factors. This provides a general framework for studying "near-efficient" multiway estimators in finite-sample settings. For higher ranks, we illustrate that our multiway estimator may not attain the CRLB; nevertheless, CP-based parametric inference remains nearly minimax optimal, with error bounds that improve on prior work by offering more favorable dependence on the CP rank. Numerical experiments corroborate near-efficiency in the rank-one case and highlight the efficiency gap in higher-rank scenarios. |
| title | Near-Efficient and Non-Asymptotic Multiway Inference |
| topic | Statistics Theory Numerical Analysis Machine Learning 62F99 (Primary) 15A69 (Secondary) |
| url | https://arxiv.org/abs/2511.05368 |