Optimal Transfer Learning for Missing Not-at-Random Matrix Completion
Not on the map. Why?
Abstract (arXiv)
We study transfer learning for matrix completion in a Missing Not-at-Random (MNAR) setting that is motivated by biological problems. The target matrix Q has entire rows and columns missing, making estimation impossible without side information. To address this, we use a noisy and incomplete source matrix P, which relates to Q via a feature shift in latent space. We consider both the active and passive sampling of rows and columns. We establish minimax lower bounds for entrywise estimation error in each setting. Our computationally efficient estimation framework achieves this lower bound for the active setting, which leverages the source data to query the most informative rows and columns of Q. This avoids the need for incoherence assumptions required for rate optimality in the passive sampling setting. We demonstrate the effectiveness of our approach through comparisons with existing algorithms on real-world biological datasets.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 31 of its 77 references that are in the map. First posted on arXiv 28 Feb 2025.
Builds on
31 of 77 references.
References · 31
- 2017Adversarial Discriminative Domain Adaptationcited by 1,311
- 2019A Comprehensive Survey on Transfer Learningcited by 1,160
- 2020What is being transferred in transfer learning?cited by 368
- 2017Community Detection and Stochastic Block Modelscited by 319
- 2020On the Theory of Transfer Learning: The Importance of Task Diversitycited by 186
- 2019Learning with Good Feature Representations in Bandits and in RL with a Generative Modelcited by 127
- 2020Spectral Methods for Data Science: A Statistical Perspectivecited by 112
- 2020Covid-19: Automatic detection from X-Ray images utilizing Transfer Learning with Convolutional Neural Networkscited by 92
- 2019Transfer Learning for Nonparametric Classification: Minimax Rate and Adaptive Classifiercited by 65
- 2019Noisy Matrix Completion: Understanding Statistical Guarantees for Convex Relaxation via Nonconvex Optimizationcited by 58
- 2022Optimally tackling covariate shift in RKHS-based nonparametric regressioncited by 54
- 2021Active Learning for Domain Adaptation: An Energy-Based Approachcited by 53
19 more
- 2021Causal Matrix Completioncited by 45
- 2022Provable Benefits of Representational Transfer in Reinforcement Learningcited by 38
- 2021Robust Transfer Learning with Pretrained Language Models through Adapterscited by 35
- 2019Missing Not at Random in Matrix Completion: The Effectiveness of Estimating Missingness Probabilities Under a Low Nuclear Norm Assumptioncited by 29
- 2024Transfer Learning for Nonparametric Regression: Non-asymptotic Minimax Analysis and Adaptive Procedurecited by 22
- 2021Matrix completion with data-dependent missingness probabilitiescited by 15
- 2021Multi-source Learning via Completion of Block-wise Overlapping Noisy Matricescited by 10
- 2019Recovering shared structure from multiple networks with unknown edge distributionscited by 8
- 2021A Systems Theory of Transfer Learningcited by 6
- 2017Matrix completion with queriescited by 5
- 2023Tackling Combinatorial Distribution Shift: A Matrix Completion Perspectivecited by 5
- 2024Kernel spectral joint embeddings for high-dimensional noisy datasets using duo-landmark integral operatorscited by 5
- 2022Best Policy Identification in Linear MDPscited by 4
- 2024Representational Transfer Learning for Matrix Completioncited by 4
- 2024Transfer Learning for Latent Variable Network Modelscited by 3
- 2024LEARNER: A Transfer Learning Method for Low-Rank Matrix Estimationcited by 3
- 2022Survey of Matrix Completion Algorithmscited by 2
- 2023Exploiting Observation Bias to Improve Matrix Completioncited by 1
- 2024Adaptive Transfer Clustering: A Unified Frameworkcited by 1
Built on by
Citing papers per year: 2025: 2.
2 papers.