Methods › General › AutoML › MDL
Minimum Description Length
MDL
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Minimum Description Length provides a criterion for the selection of models, regardless of their complexity, without the restrictive assumption that the data form a sample from a 'true' distribution.
Extracted from scholarpedia
Source:
Paper: J. Rissanen (1978) Modeling by the shortest data description. Automatica 14, 465-471
Book: P. D. Grünwald (2007) The Minimum Description Length Principle, MIT Press, June 2007, 570 pages
In Syntology no code under this exact name (no_code; paper_only). The archive credits no paper with an arXiv id for this method, so whether this answer (about arXiv:2602.07520) is about this method is not checked; it does not say whether this method has code.
From the lookup's note on this name: The same name also belongs to “information-theoretic probing with minimum description length (MDL)”, a method in the paper “Information-Theoretic Probing with Minimum Description Length” (arXiv:2003.12298, 333 citations), which the lookup finds cited far more than the paper this answer is about (0 citations), so this answer may be about a different sense of the name. For arXiv:2003.12298: its page on this site · ask the lookup about it.
Origin paper of this answer, arXiv:2602.07520 (its page on Syntology).
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 97 · with a code link: 22 · where Syntology ran a sample: 4 (3 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (4 of 97 tagged: 3 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 97 of 97, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
Bridging Predictive Coding and MDL: A Two-Part Code Framework for Deep Learning 20 May 2025 · 0 repositories · arXiv:2505.14635
-
A Minimum Description Length Approach to Regularization in Neural Networks 19 May 2025 · 1 repository · arXiv:2505.13398Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)
-
A Theory of Machine Understanding via the Minimum Description Length Principle 1 Apr 2025 · 0 repositories · arXiv:2504.00395
-
A Materials Map Integrating Experimental and Computational Data via Graph-Based Machine Learning for Enhanced Materials Discovery 10 Mar 2025 · 0 repositories · arXiv:2503.07378
-
Comparative Analysis of MDL-VAE vs. Standard VAE on 202 Years of Gynecological Data 25 Feb 2025 · 0 repositories · arXiv:2502.18412
-
On Calibration in Multi-Distribution Learning 18 Dec 2024 · 0 repositories · arXiv:2412.14142
-
AdaptiveMDL-GenClust: A Robust Clustering Framework Integrating Normalized Mutual Information and Evolutionary Algorithms 26 Nov 2024 · 0 repositories · arXiv:2412.05305
-
Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations with MDL-SAEs 15 Oct 2024 · 0 repositories · arXiv:2410.11179
-
Neural Networks Generalize on Low Complexity Data 19 Sep 2024 · 0 repositories · arXiv:2409.12446
-
MDL-Pool: Adaptive Multilevel Graph Pooling Based on Minimum Description Length 16 Sep 2024 · 0 repositories · arXiv:2409.10263
-
A Systematic Review of Intermediate Fusion in Multimodal Deep Learning for Biomedical Applications 2 Aug 2024 · 0 repositories · arXiv:2408.02686
-
Coding for Intelligence from the Perspective of Category 1 Jul 2024 · 0 repositories · arXiv:2407.01017
-
Crocodile: Cross Experts Covariance for Disentangled Learning in Multi-Domain Recommendation 21 May 2024 · 0 repositories · arXiv:2405.12706
-
Probabilistic Truly Unordered Rule Sets 18 Jan 2024 · 1 repository · arXiv:2401.09918
-
Skin cancer diagnosis using NIR spectroscopy data of skin lesions in vivo using machine learning algorithms 2 Jan 2024 · 0 repositories · arXiv:2401.01200
-
Distribution-Dependent Rates for Multi-Distribution Learning 20 Dec 2023 · 0 repositories · arXiv:2312.13130
-
Optimal Multi-Distribution Learning 8 Dec 2023 · 0 repositories · arXiv:2312.05134
-
Exploring the hierarchical structure of human plans via program generation 30 Nov 2023 · 2 repositories · arXiv:2311.18644
-
Bridging Algorithmic Information Theory and Machine Learning: A New Approach to Kernel Learning 21 Nov 2023 · 0 repositories · arXiv:2311.12624
-
Improved MDL Estimators Using Fiber Bundle of Local Exponential Families for Non-exponential Families 7 Nov 2023 · 0 repositories · arXiv:2311.03852
-
KG-MDL: Mining Graph Patterns in Knowledge Graphs with the MDL Principle 22 Sep 2023 · 0 repositories · arXiv:2309.12908
-
Decoupled Training: Return of Frustratingly Easy Multi-Domain Learning 19 Sep 2023 · 0 repositories · arXiv:2309.10302
-
Variational Density Propagation Continual Learning 22 Aug 2023 · 0 repositories · arXiv:2308.11801
-
A scoping review on multimodal deep learning in biomedical images and texts 14 Jul 2023 · 0 repositories · arXiv:2307.07362
-
Generating Parametric BRDFs from Natural Language Descriptions 19 Jun 2023 · 1 repository · arXiv:2306.15679
-
Perturbation-Based Two-Stage Multi-Domain Active Learning 19 Jun 2023 · 0 repositories · arXiv:2306.10700
-
The Whole Is Greater than the Sum of Its Parts: Improving Music Source Separation by Bridging Network 13 May 2023 · 1 repository · arXiv:2305.07855
-
Multi-Domain Learning From Insufficient Annotations 4 May 2023 · 0 repositories · arXiv:2305.02757
-
A Comprehensive and Versatile Multimodal Deep Learning Approach for Predicting Diverse Properties of Advanced Materials 29 Mar 2023 · 0 repositories · arXiv:2303.16412
-
Learning the Finer Things: Bayesian Structure Learning at the Instantiation Level 8 Mar 2023 · 0 repositories · arXiv:2303.04339
-
Computing formation enthalpies through an explainable machine learning method: the case of Lanthanide Orthophosphates solid solutions 7 Mar 2023 · 0 repositories · arXiv:2303.03748
-
Evaluating Representations with Readout Model Switching 19 Feb 2023 · 0 repositories · arXiv:2302.09579
-
Fast and fully-automated histograms for large-scale data sets 27 Dec 2022 · 0 repositories · arXiv:2212.13524
-
Multi-timescale Event Detection in Nonintrusive Load Monitoring based on MDL Principle 19 Nov 2022 · 0 repositories · arXiv:2211.10721
-
Sequential Learning Of Neural Networks for Prequential MDL 14 Oct 2022 · 0 repositories · arXiv:2210.07931
-
Minimum Description Length Control 17 Jul 2022 · 0 repositories · arXiv:2207.08258
-
Improving the Robustness and Generalization of Deep Neural Network with Confidence Threshold Reduction 2 Jun 2022 · 0 repositories · arXiv:2206.00913
-
Rotated Object Detection via Scale-invariant Mahalanobis Distance in Aerial Images 2 Apr 2022 · 0 repositories · arXiv:2204.00840
-
Extending the Use of MDL for High-Dimensional Problems: Variable Selection, Robust Fitting, and Additive Modeling 26 Jan 2022 · 0 repositories · arXiv:2201.11171
-
The whole and the parts: the MDL principle and the a-contrario framework 13 Dec 2021 · 0 repositories · arXiv:2112.06853
-
First Steps of an Approach to the ARC Challenge based on Descriptive Grid Models and the Minimum Description Length Principle 1 Dec 2021 · 1 repository · arXiv:2112.00848
-
Rethinking Hard-Parameter Sharing in Multi-Domain Learning 23 Jul 2021 · 0 repositories · arXiv:2107.11359
-
Prequential MDL for Causal Structure Learning with Neural Networks 2 Jul 2021 · 0 repositories · arXiv:2107.05481
-
Multi-Domain Active Learning: Literature Review and Comparative Study 25 Jun 2021 · 1 repository · arXiv:2106.13516
-
Robust subgroup discovery 25 Mar 2021 · 2 repositories · arXiv:2103.13686
-
PAC-learning gains of Turing machines over circuits and neural networks 23 Mar 2021 · 0 repositories · arXiv:2103.12686
-
Rissanen Data Analysis: Examining Dataset Characteristics via Description Length 5 Mar 2021 · 1 repository · arXiv:2103.03872Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
Multi-Domain Learning by Meta-Learning: Taking Optimal Steps in Multi-Domain Loss Landscapes by Inner-Loop Learning 25 Feb 2021 · 0 repositories · arXiv:2102.13147
-
Mapping Network States Using Connectivity Queries 7 Dec 2020 · 1 repository · arXiv:2012.03413
-
Mint: MDL-based approach for Mining INTeresting Numerical Pattern Sets 30 Nov 2020 · 0 repositories · arXiv:2011.14843
-
Detecting Hierarchical Changes in Latent Variable Models 18 Nov 2020 · 0 repositories · arXiv:2011.09465
-
Experimental validation of MDL emulation and estimation techniques for SDM transmission systems 29 Oct 2020 · 0 repositories · arXiv:2010.15496
-
All for One and One for All: Improving Music Separation by Bridging Networks 8 Oct 2020 · 5 repositories · arXiv:2010.04228Syntology official (archive's flag): 7 ran · 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 10 harvested samples)
-
More Diverse Means Better: Multimodal Deep Learning Meets Remote Sensing Imagery Classification 12 Aug 2020 · 1 repository · arXiv:2008.05457
-
Improving Performance of Relation Extraction Algorithm via Leveled Adversarial PCNN and Database Expansion 29 Jul 2020 · 0 repositories · arXiv:2007.15084
-
The Minimum Description Length Principle for Pattern Mining: A Survey 28 Jul 2020 · 0 repositories · arXiv:2007.14009
-
What and Where: Learn to Plug Adapters via NAS for Multi-Domain Learning 24 Jul 2020 · 0 repositories · arXiv:2007.12415
-
Discovering outstanding subgroup lists for numeric targets using MDL 16 Jun 2020 · 3 repositories · arXiv:2006.09186
-
Unsupervised Discretization by Two-dimensional MDL-based Histogram 2 Jun 2020 · 1 repository · arXiv:2006.01893
-
Information-Theoretic Probing with Minimum Description Length 27 Mar 2020 · 2 repositories · arXiv:2003.12298Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified (of 5 harvested samples) · 5 pointer-only (licence)
-
Unified Multi-Domain Learning and Data Imputation using Adversarial Autoencoder 15 Mar 2020 · 0 repositories · arXiv:2003.07779
-
Stance Detection Benchmark: How Robust Is Your Stance Detection? 6 Jan 2020 · 1 repository · arXiv:2001.01565Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 10 harvested samples) · 2 pointer-only (licence)
-
Collaborative Generated Hashing for Market Analysis and Fast Cold-start Recommendation 1 Jan 2020 · 0 repositories
-
Towards a Robust Classifier: An MDL-Based Method for Generating Adversarial Examples 11 Dec 2019 · 0 repositories · arXiv:1912.05945
-
Causal Inference via Conditional Kolmogorov Complexity using MDL Binning 31 Oct 2019 · 0 repositories · arXiv:1911.00332
-
Descriptive Dimensionality and Its Characterization of MDL-based Learning and Change Detection 25 Oct 2019 · 0 repositories · arXiv:1910.11540
-
An MDL-Based Classifier for Transactional Datasets with Application in Malware Detection 9 Oct 2019 · 0 repositories · arXiv:1910.03751
-
Model-aided Deep Neural Network for Source Number Detection 29 Sep 2019 · 0 repositories · arXiv:1909.13273
-
Minimum Description Length Revisited 21 Aug 2019 · 0 repositories · arXiv:1908.08484
-
Identifying Linear Models in Multi-Resolution Population Data using Minimum Description Length Principle to Predict Household Income 10 Jul 2019 · 1 repository · arXiv:1907.05234
-
Sentence Length 22 May 2019 · 1 repository · arXiv:1905.09139
-
Budget-Aware Adapters for Multi-Domain Learning 15 May 2019 · 0 repositories · arXiv:1905.06242
-
Summarizing Event Sequences with Serial Episodes: A Statistical Model and an Application 1 Apr 2019 · 0 repositories · arXiv:1904.00516
-
Multi-Domain Adversarial Learning 21 Mar 2019 · 1 repository · arXiv:1903.09239
-
Differential Description Length for Hyperparameter Selection in Machine Learning 13 Feb 2019 · 0 repositories · arXiv:1902.04699
-
The Long and the Short of It: Summarising Event Sequences with Serial Episodes 7 Feb 2019 · 0 repositories · arXiv:1902.02834
-
From-Below Boolean Matrix Factorization Algorithm Based on MDL 28 Jan 2019 · 0 repositories · arXiv:1901.09567
-
We Are Not Your Real Parents: Telling Causal from Confounded using MDL 21 Jan 2019 · 0 repositories · arXiv:1901.06950
-
Distributed Inference for Linear Support Vector Machine 29 Nov 2018 · 0 repositories · arXiv:1811.11922
-
A tutorial on MDL hypothesis testing for graph analysis 31 Oct 2018 · 0 repositories · arXiv:1810.13163
-
Finite-sample risk bounds for maximum likelihood estimation with arbitrary penalties 29 Dec 2017 · 0 repositories · arXiv:1712.10087
-
AIXIjs: A Software Demo for General Reinforcement Learning 22 May 2017 · 1 repository · arXiv:1705.07615
-
Scalable Exact Parent Sets Identification in Bayesian Networks Learning with Apache Spark 18 May 2017 · 1 repository · arXiv:1705.06390
-
Causal Inference on Multivariate and Mixed-Type Data 21 Feb 2017 · 0 repositories · arXiv:1702.06385
-
Unifying Multi-Domain Multi-Task Learning: Tensor and Neural Network Perspectives 28 Nov 2016 · 0 repositories · arXiv:1611.09345
-
Minimum Description Length Principle in Supervised Learning with Application to Lasso 11 Jul 2016 · 0 repositories · arXiv:1607.02914
-
Fast Rates for General Unbounded Loss Functions: from ERM to Generalized Bayes 1 May 2016 · 0 repositories · arXiv:1605.00252
-
A C++ library for Multimodal Deep Learning 22 Dec 2015 · 0 repositories · arXiv:1512.06927
-
Higher-order asymptotics for the parametric complexity 1 Oct 2015 · 0 repositories · arXiv:1510.00112
-
Incorporating Type II Error Probabilities from Independence Tests into Score-Based Learning of Bayesian Network Structure 12 May 2015 · 0 repositories · arXiv:1505.02870
-
A Unified Perspective on Multi-Domain and Multi-Task Learning 23 Dec 2014 · 0 repositories · arXiv:1412.7489
-
Joint Energy-based Detection and Classificationon of Multilingual Text Lines 23 Jul 2014 · 0 repositories · arXiv:1407.6082
-
SparsityBoost: A New Scoring Function for Learning Bayesian Network Structure 26 Sep 2013 · 0 repositories · arXiv:1309.6820
-
Extending Universal Intelligence Models with Formal Notion of Representation 6 Jun 2013 · 0 repositories · arXiv:1306.1557
-
A Bayesian Approach to Learning Bayesian Networks with Local Structure 6 Feb 2013 · 0 repositories · arXiv:1302.1528
-
Parsimonious module inference in large networks 19 Dec 2012 · 1 repository · arXiv:1212.4794
-
Discrete MDL Predicts in Total Variation 1 Dec 2009 · 0 repositories
Tasks archive 2025-07-28
20 shown of 101 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections