Toward Scalable and Valid Conditional Independence Testing with Spectral Representations

• URL: http://arxiv.org/abs/2512.19510v1
• Date: Mon, 22 Dec 2025 16:05:18 GMT
• Title: Toward Scalable and Valid Conditional Independence Testing with Spectral Representations
• Authors: Alek Frohlich, Vladimir Kostic, Karim Lounici, Daniel Perazzo, Massimiliano Pontil,
• Abstract summary: Conditional independence (CI) is untestable in many settings without additional assumptions.<n>We introduce a practical bi-level contrastive algorithm to learn representations derived from the singular value decomposition of the partial covariance operator.<n>Preliminary experiments suggest that this approach offers a practical and statistically grounded path toward scalable CI testing.
• Score: 25.258360465513338
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Conditional independence (CI) is central to causal inference, feature selection, and graphical modeling, yet it is untestable in many settings without additional assumptions. Existing CI tests often rely on restrictive structural conditions, limiting their validity on real-world data. Kernel methods using the partial covariance operator offer a more principled approach but suffer from limited adaptivity, slow convergence, and poor scalability. In this work, we explore whether representation learning can help address these limitations. Specifically, we focus on representations derived from the singular value decomposition of the partial covariance operator and use them to construct a simple test statistic, reminiscent of the Hilbert-Schmidt Independence Criterion (HSIC). We also introduce a practical bi-level contrastive algorithm to learn these representations. Our theory links representation learning error to test performance and establishes asymptotic validity and power guarantees. Preliminary experiments suggest that this approach offers a practical and statistically grounded path toward scalable CI testing, bridging kernel-based theory with modern representation learning.

Related papers

• Nonparametric Identification and Inference for Counterfactual Distributions with Confounding [6.997978440999076]
  We propose nonparametric identification and semiparametric estimation of joint potential outcome in the presence of confounding.<n>By bridging classical semiparametric theory with modern representation learning, this work provides a robust statistical foundation for distributional and counterfactual inference in complex causal systems.
  arXiv  Detail & Related papers  (2026-02-17T05:00:13Z)
• On the Limits of Test-Time Compute: Sequential Reward Filtering for Better Inference [71.09125259964684]
  Test-time compute (TTC) has become an increasingly prominent paradigm for enhancing large language models (LLMs)<n>We study reward-filtered sequential inference, a simple procedure that selectively incorporates only high-reward generations into the context.<n>On the theoretical side, we show that reward-filtered sequential inference yields strictly stronger guarantees than standard TTC paradigms.
  arXiv  Detail & Related papers  (2025-12-04T08:21:33Z)
• Theoretical Bounds for Stable In-Context Learning [0.0]
  In-context learning (ICL) is flexible but its reliability is sensitive to prompt length.<n>This paper establishes a non-asymptotic lower bound that links the minimal number of demonstrations to ICL stability.<n>We propose a two-stage observable estimator with a one-shot calibration that produces practitioner-ready prompt-length estimates.
  arXiv  Detail & Related papers  (2025-09-25T02:25:05Z)
• A Sample Efficient Conditional Independence Test in the Presence of Discretization [54.047334792855345]
  Conditional Independence (CI) tests directly to discretized data can lead to incorrect conclusions.<n>Recent advancements have sought to infer the correct CI relationship between the latent variables through binarizing observed data.<n>Motivated by this, this paper introduces a sample-efficient CI test that does not rely on the binarization process.
  arXiv  Detail & Related papers  (2025-06-10T12:41:26Z)
• Kernel conditional tests from learning-theoretic bounds [16.813275168865953]
  We propose a framework for hypothesis testing on conditional probability distributions.<n>We then use to construct statistical tests of functionals of conditional distributions.<n>Our results establish a comprehensive foundation for conditional testing on functionals.
  arXiv  Detail & Related papers  (2025-06-04T12:53:13Z)
• Model-free Methods for Event History Analysis and Efficient Adjustment (PhD Thesis) [55.2480439325792]
  This thesis is a series of independent contributions to statistics unified by a model-free perspective.<n>The first chapter elaborates on how a model-free perspective can be used to formulate flexible methods that leverage prediction techniques from machine learning.<n>The second chapter studies the concept of local independence, which describes whether the evolution of one process is directly influenced by another.
  arXiv  Detail & Related papers  (2025-02-11T19:24:09Z)
• Towards Practical Control of Singular Values of Convolutional Layers [65.25070864775793]
  Convolutional neural networks (CNNs) are easy to train, but their essential properties, such as generalization error and adversarial robustness, are hard to control. Recent research demonstrated that singular values of convolutional layers significantly affect such elusive properties. We offer a principled approach to alleviating constraints of the prior art at the expense of an insignificant reduction in layer expressivity.
  arXiv  Detail & Related papers  (2022-11-24T19:09:44Z)
• On Medians of (Randomized) Pairwise Means [8.497456090408084]
  Tournament procedures, recently introduced in Lugosi & Mendelson, offer an appealing alternative to the principle of Empirical Risk Minimization in machine learning. This paper extends this approach to address other learning problems, in particular for which the performance criterion takes the form of an expectation over pairs of observations.
  arXiv  Detail & Related papers  (2022-11-01T17:18:15Z)
• MaxMatch: Semi-Supervised Learning with Worst-Case Consistency [149.03760479533855]
  We propose a worst-case consistency regularization technique for semi-supervised learning (SSL) We present a generalization bound for SSL consisting of the empirical loss terms observed on labeled and unlabeled training data separately. Motivated by this bound, we derive an SSL objective that minimizes the largest inconsistency between an original unlabeled sample and its multiple augmented variants.
  arXiv  Detail & Related papers  (2022-09-26T12:04:49Z)
• Recursive Causal Structure Learning in the Presence of Latent Variables and Selection Bias [27.06618125828978]
  We consider the problem of learning the causal MAG of a system from observational data in the presence of latent variables and selection bias. We propose a novel computationally efficient constraint-based method that is sound and complete. We provide experimental results to compare the proposed approach with the state of the art on both synthetic and real-world structures.
  arXiv  Detail & Related papers  (2021-10-22T19:49:59Z)
• Good Classifiers are Abundant in the Interpolating Regime [64.72044662855612]
  We develop a methodology to compute precisely the full distribution of test errors among interpolating classifiers. We find that test errors tend to concentrate around a small typical value $varepsilon*$, which deviates substantially from the test error of worst-case interpolating model. Our results show that the usual style of analysis in statistical learning theory may not be fine-grained enough to capture the good generalization performance observed in practice.
  arXiv  Detail & Related papers  (2020-06-22T21:12:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.