mlsanityData to 14 Oct 2026

RCShift: Certifying When Partial Linkage Suffices for Finite-Sample Decisions

arXiv 2609.26207 ↗First posted 11 Aug 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Systems with costly gold outcomes and cheaper auxiliary observations must decide how much record linkage to retain. Complete pairing retains every joint counter, while separate margins retain none. Neither endpoint is calibrated to a declared finite-sample decision. Universal reconstruction can retain cycle directions invisible to the likelihood-ratio family. Family-exact storage can exceed what the decision requires because certified residual loss may fit within finite-sample slack. We introduce RCShift, which certifies two routes to sufficiency under a declared observation contract. Its exact mode characterizes minimum-cost family-exact storage through LR-visible cycle directions. Its approximate mode bounds reverse Le Cam deficiency. Its integer mode certifies whether a chosen set preserves the full experiment's minimum integer record count at specified size and power. In a rank-two witness, one aligned counter preserves a four-record minimum. An equal-cost misaligned counter and the margins require eleven records, while universal reconstruction requires two counters. A local perturbation has positive reverse deficiency yet retains the four-record minimum. Proof-checked scheduling bounds instantiate the contract before gold computation and yield exact reconstruction on the admitted tree support. RCShift turns partial-linkage storage into decision-calibrated measurement design for the declared family, costs, target, and common strictly positive support.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 34 references that are in the map. First posted on arXiv 11 Aug 2026.

Builds on

18 of 34 references.

References · 18

  1. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,273
  2. 2016Deep Variational Information Bottleneckcited by 930
  3. 2018MINE: Mutual Information Neural Estimationcited by 683
  4. 2017Learning Combinatorial Optimization Algorithms over Graphscited by 561
  5. 2019On Variational Bounds of Mutual Informationcited by 559
  6. 2020POMO: Policy Optimization with Multiple Optima for Reinforcement Learningcited by 348
  7. 2019Exact Combinatorial Optimization with Graph Convolutional Neural Networkscited by 318
  8. 2019On Mutual Information Maximization for Representation Learningcited by 316
  9. 2018Combinatorial Optimization with Graph Convolutional Networks and Guided Tree Searchcited by 183
  10. 2020Graph Information Bottleneckcited by 168
  11. 2020A Theory of Usable Information Under Computational Constraintscited by 162
  12. 2020Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learningcited by 140
6 more
  1. 2018EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAEcited by 87
  2. 2020Active Feature Acquisition with Generative Surrogate Modelscited by 54
  3. 2020Learning Optimal Representations with the Decodable Information Bottleneckcited by 33
  4. 2019Flow Models for Arbitrary Conditional Likelihoodscited by 30
  5. 2023Acquisition Conditioned Oracle for Nongreedy Active Feature Acquisitioncited by 19
  6. 2022Certifying Parity Reasoning Efficiently Using Pseudo-Boolean Proofscited by 14

Built on by

Not cited yet.