Conditional Independence

Follow this topic Ask about this topic

Momentum

6 papers in the last four weeks, up 20% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 35

All topics

On the Relaxation of Conditional Independence Assumption for Image Segmentation
Sep 30, 2026Zixun Wang, Ben DaiSemantic Segmentation Conditional Independence
Department of Statistics and Data Science The Chinese University of Hong Kong
Beyond Conditional Independence: Root Cause Analysis with Deep Causal Models
Sep 29, 2026Md Musfiqur Rahman, Kenneth Lee, Ziwei Jiang +3Root Cause Analysis Conditional Independence
Electrical and Computer Engineering, Purdue University · Computer Science, Johns Hopkins University · Intuit AI Research +1
Domain-Adapted Diffusion Models for Conditional Independence Testing
Sep 27, 2026Yanfeng Yang, Junda Zhao, Yijie Gao +8Text-Conditioned Diffusion Model Conditional Independence
The Graduate University for Advanced Studies, SOKENDAI, Tokyo, Japan · The Institute of Statistical Mathematics, Tokyo, Japan · East China Normal University, Shanghai, China +4
Auditing Bayesian Graph Alignment: Diagnostic Comparisons and Reference Failure
Sep 19, 2026Melika Gorgi, Kourosh MirsohiConditional Independence Diagnosis
Center for Complex Biological Systems University of California, Irvine Irvine, CA 92697, USA · Department of Computer Science University of California, Irvine Irvine, CA 92697, USA
On the Identifiability of Mixed Ordinal and Exponential Family Causal DAGs under Linear Parametric Models
Sep 16, 2026Sambit Mishra, Urbashi MitraLinear Structural Equation Models Identifiability
Ming Hsieh Department of Electrical and Computer Engineering University of Southern California Los Angeles, CA 90089, USA
OBC-Prune: Outcome-Based Calibration for Large Reasoning Model Pruning
Sep 15, 2026Ha Lan Nguyen, Huy Hoang Tran, Trac-Duy Tran +1Conditional Independence
VinUniversity · Johns Hopkins University
Debiased Inference for AI-Generated Data without Gold-Standard Labels: Identification via Multiple Imperfect Measurements
Aug 18, 2026Naoki Egami, Sooahn ShinStatistical Inference Large Language Model Annotations
Department of Political Science and Statistics and Data Science Center, Massachusetts Institute of Technology, Cambridge, MA 02139 · Department of Political Science, Massachusetts Institute of Technology, Cambridge, MA 02139
Foundations of Independent Component Analysis
Aug 13, 2026Patrick ForréIndependent Component Analysis Identifiability
AI4Science Lab Korteweg-de Vries Institute for Mathematics University of Amsterdam
Agent Behavioral Contracts II: Certifying Compositional Reliability Without Assuming Independence
Aug 13, 2026Varun Pratap Bhardwaj, Garima Singh, Arun Pratap BhardwajConditional Independence Contracts
Qualixar / Independent Researcher, India · Independent Researcher, India
Thermodynamics of Learning: A Typed Four-Component Accounting of Memory, Fit, and Value
Aug 13, 2026Akihito SudoValue Ledger
ZeroStruct Inc.
Conditional Independence Tests for Constraint-Based Causal Discovery: A Survey
Aug 11, 2026Pavel Averin, Theodoros Moysiadis, Ioannis KatakisConditional Independence Causal Discovery Methods
Department of Computer Science School of Sciences and Engineering University of Nicosia 2417, Nicosia, Cyprus
High-Order Markov Blanket Discovery via a k-Order Relaxation of the Faithfulness Assumption
Jul 29, 2026Loong Kuan Lee, Ragavi Krishnamoorthy, Nico PiatkowskiConditional Independence Markov
Hybrid Intelligence, Fraunhofer IAIS, Sankt Augustin, Germany
A Characterization of the Orthocomplement of the Tangent Space of Semiparametric Markov Models
Jul 26, 2026Trung Phung, Ilya ShpitserProbabilistic Graphical Models Influence Function
Computer Science Department, Johns Hopkins University, Baltimore, Maryland, USA
A Causal Markov Condition for Value
Jul 18, 2026Olav Benjamin VassendConditional Independence Causal Graph
University of Inland Norway
Relaxing Faithfulness with Intervention-Only Causal Discovery
Jul 13, 2026Bijan Mazaheri, Jiaqi Zhang, Caroline UhlerCausal Discovery Methods Conditional Independence
Thayer School of Engineering, Dartmouth College, Hanover, New Hampshire, USA · Schmidt Center, Broad Institute of MIT and Harvard, Cambridge, Massachusetts, USA · Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA
The Moving Target: A Longitudinal Audit of Trustworthiness Drift Across Twelve Checkpoints of Open-Source Chat LLMs
Jul 1, 2026Zhichao Fan, Yanhang Li, Zexin Zhuang +2Large Language Model Reliability AI Trustworthiness
University of Illinois Urbana-Champaign · Northeastern University · Southern Methodist University +2
Learning Gaussian Graphical Models from a Glauber Trajectory Without Mixing
Jun 30, 2026Eric Shen, Tony Wu, Mahbod Majid +1Probabilistic Graphical Models Conditional Independence
MIT
Statistical Matching via Schrödinger Bridge beyond Conditional Independence
Jun 22, 2026Eunho Koo, Tongseok Lim, Jinwon SohnImputation Conditional Independence
Department of Big Data Convergence Chonnam National University · Mitch Daniels School of Business Purdue University · Booth School of Business University of Chicago
Sequential Kernel-based Conditional Independence Testing via Adaptive Betting
Jun 17, 2026Zheng He, Danica J. SutherlandConditional Independence Two-Sample Testing
Department of Computer Science, University of British Columbia, Vancouver, Canada · Alberta Machine Intelligence Institute, Edmonton, Canada
Fast Nonparametric Conditional Independence Testing via Two-Stage Regression
Jun 16, 2026Eric V. StroblCausal Discovery Methods Conditional Independence
Department of Biomedical Informatics, University of Pittsburgh, Pittsburgh, PA 15213, USA
Identifiability and Estimation for Unlabeled Finite Mixtures under Marginal Independence
Jun 6, 2026Takafumi Kanamori, Yushi Hirose, Shohei YamamotoMixture Models Identifiability
Department of Mathematical and Computing Science, Institute of Science Tokyo · RIKEN Center for Advanced Intelligence Project
A Martingale Kernel Independence Test
May 21, 2026Felix Laumann, Zhaolu Liu, Mauricio BarahonaTwo-Sample Testing Conformal Test Martingales
Imperial College London
Score-Based Causal Discovery of Latent Variable Causal Models
May 19, 2026Ignavier Ng, Xinshuai Dong, Haoyue Dai +3Causal Discovery Methods Causal Representation Learning
Carnegie Mellon University · University of California, San Diego · Mohamed bin Zayed University of Artificial Intelligence
Marginal Alignment Does Not Guarantee Joint-Distribution Fidelity: An Official-Reference Audit of Nemotron-Personas-Korea with Cross-Locale Replication
May 15, 2026Joonhyung BaeDemographics Persona Consistency
Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea
A Recursive Decomposition Framework for Causal Structure Learning in the Presence of Latent Variables
May 11, 2026Zheng Li, Feng Xie, Shenglan Nie +3Causal Discovery Methods Conditional Independence
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China · Department of Applied Statistics, Beijing Technology and Business University, Beijing, China · College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China
The Pokémon Theorem and other Fairness Impossibility Results
May 9, 2026Daniel Matsui Smola, Alex SmolaAlgorithmic Fairness Impossibility
Department of Computer Science University of Washington Seattle, WA · Boson AI Santa Clara, CA
Data-Driven Covariate Selection for Nonparametric and Cycle-Agnostic Causal Effect Estimation
May 7, 2026Ana Leticia Garcez Vicente, Gijs van Seeventer, Saber SalehkaleybarCovariate Balancing Causal Inferences
Leiden University Netherlands
Beyond the Independence Assumption: Finite-Sample Guarantees for Deep Q-Learning under $τ$ -Mixing
May 7, 2026Leon Halgryn, Sophie Langer, Janusz M. Meylahn +1Deep Q-Networks Deterministic Replay
University of Twente · Department of Applied Mathematics University of Twente · Ruhr-Universität Bochum +1
PAIR-CI: Calibrated Conditional Independence Testing for Causal Discovery with Incomplete Data
May 6, 2026Thomas S. Robinson, Ranjit LallConditional Independence Imputation
Department of Methodology London School of Economics and Political Science London, UK · Department of Politics and International Relations University of OxfordMay Oxford, UK
Causal discovery under mean independence and linearity
May 6, 2026Geert Mesters, Alvaro Ribot, Anna Seigal +1Causal Discovery Methods Conditional Independence
Deep-testing: the case of dependence detection
Apr 29, 2026Gery Geenens, Pierre Lafaye de Micheaux, Ivan Muyun ZouTwo-Sample Testing Conditional Independence
School of Mathematics and statistics, UNSW Sydney, Australia
Causal Discovery as Dialectical Aggregation: A Quantitative Argumentation Framework
Apr 26, 2026Sheng Wei, Yulin Chen, Beishui LiaoCausal Discovery Methods Argumentation Frameworks
The College of Computer Science and Technology, Zhejiang University · School of Philosophy, Zhejiang University · ZLAIRE, Zhejiang University +1
Design of Experiment for Discovering Directed Mixed Graph
Sep 2, 2025Haijie Xu, Chen ZhangCausal Discovery Methods Conditional Independence
Department of Industrial Engineering Tsinghua University
Meta-Dependence in Conditional Independence Testing
Apr 17, 2025Bijan Mazaheri, Jiaqi Zhang, Caroline UhlerConditional Independence
Thayer School of Engineering, Dartmouth College, Hanover, New Hampshire, USA · Schmidt Center, Broad Institute of MIT and Harvard, Cambridge, Massachusetts, USA · Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA
SPARC: Scalable Path-Specific Counterfactual Fairness via Causal Conditional Independence
Dec 6, 2024Bowei Tian, Yexiao He, Ziyao Wang +3Algorithmic Fairness Causal Inferences
University of Maryland, College Park, MD 20742, USA · Clemson University, Clemson, SC 29634, USA

Sep 30, 2026, cs.CVJ/K move · Enter open · S save

On the Relaxation of Conditional Independence Assumption for Image Segmentation

Zixun Wang, Ben Dai

Department of Statistics and Data Science The Chinese University of Hong Kong

Semantic Segmentation Conditional Independence Assumptions Soft

Open paper AskPDF arXiv

In semantic segmentation, a recent line of RankSEG methods directly optimizes Dice/IoU scores at inference time, improving alignment with evaluation metrics without modifying model training. Despite its theoretical and empirical success, RankSEG relies on the restrictive Conditional Independence Assumption (CIA), which ignores crucial label correlations and therefore degrades performance in ambiguous or low-contrast scenarios. However, accounting for full label dependence is computationally prohibitive, requiring

\mathcal{O}(d^3)

time. To address this, we replace the CIA with a Spatially Localized Dependence (SLD) structure that captures local label correlations while keeping the dependence model tractable. We further overcome the remaining computational bottleneck via a Reciprocal Moment Approximation coupled with a novel fixed-point optimization strategy that eliminates exhaustive search. The proposed algorithm achieves a highly practical

\mathcal{O}(d \log d)

complexity and consistently outperforms conventional argmax and CIA-based RankSEG across diverse segmentation benchmarks. Improvements are significant in low-contrast or small-object scenarios, where label dependence offers valuable signals complementary to image information for accurate segmentation. The code of experiments is available at https://github.com/ZixunWang/RankSEG-DEP.

Momentum

Related topics

Latest papers 35