A tutorial on using MDL for graph analysis, focusing on clique size.
problem Analyzing the size of the largest clique in graphs.
method MDL principle applied to graph analysis.
result Interpretation of MDL results and common pitfalls.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
169,051 papers · 148 categories
Trend · papers per month
48 results for “MDL Principle”
A new BMF algorithm outperforms existing methods using MDL.
problem Developing a BMF algorithm that performs well across multiple metrics.
method From-below Boolean matrix factorization algorithm based on MDL principle.
result The proposed algorithm outperforms existing methods in various experiments.
This paper extends the work in [Suzuki, 1996] and presents an efficient depth-first branch-and-bound algorithm for learning Bayesian network structures, based on the minimum description length (MDL) principle, for a given (consistent) variable ordering. The algorithm exhaustively searches through all network structures…
The minimum description length (MDL) principle in supervised learning is studied. One of the most important theories for the MDL principle is Barron and Cover's theory (BC theory), which gives a mathematical justification of the MDL principle. The original BC theory, however, can be applied to supervised learning only …
A comprehensive guide to MDL principle, a statistical inference theory.
problem Statistical inference and pattern recognition.
method MDL principle, model selection, hypothesis testing, averaging.
result Unified perspective on various statistical methods.
MDL principle aids in learning neural network-based causal structures.
problem Learning causal relationships from observations with neural networks.
method Prequential minimum description length (MDL) principle.
result Competitive results on synthetic and real-world data, often recovering correct structure.
FedSLIM optimizes compact pattern models across distributed databases without sharing raw data.
problem Privacy-preserving federated descriptive analytics for data silos.
method Federated MDL-based framework using SLIM principle.
result FedSLIM variants preserve high-quality compression structure and recover globally informative patterns.
The Minimum Description Length (MDL) principle selects the model that has the shortest code for data plus model. We show that for a countable class of models, MDL predictions are close to the true distribution in a strong sense. The result is completely general. No independence, ergodicity, stationarity, identifiabilit…
Designs a classifier for malware detection using MDL principle.
problem Static malware detection in PE files.
method Clustering, closed frequent pattern mining, MDL principle for compression.
result Our classifier performs close to deep neural networks.
We analyze differences between two information-theoretically motivated approaches to statistical inference and model selection: the Minimum Description Length (MDL) principle, and the Minimum Message Length (MML) principle. Based on this analysis, we present two revised versions of MML: a pointwise estimator which give…
Proposes a new method for two-dimensional data discretization.
problem Discretization of multi-dimensional data, especially when dimensions are dependent.
method PALM algorithm, which alternately partitions and merges regions using the MDL principle.
result PALM accurately reveals ground truth partitions and approximates well outside the model class.
A new complexity measure MDL-COMP for overparameterized models improves generalization performance.
problem Complexity measures based on Rissanen's MDL principle are not well-suited for overparameterized models.
method Developed a novel MDL-based complexity (MDL-COMP) for overparameterized models, defined via an optimality criterion over Ridge estimators.
result MDL-COMP scales linearly with when , but exponentially smaller for ; it upper bounds in-sample MSE.
We tackle the problem of penalty selection of regularization on the basis of the minimum description length (MDL) principle. In particular, we consider that the design space of the penalty function is high-dimensional. In this situation, the luckiness-normalized-maximum-likelihood(LNML)-minimization approach is favorab…
New model explains how concepts grow based on experience.
problem Existing models assume fixed representation; new model allows for growth.
method Geometric framework with MDL criterion for basis extension.
result Conceptual growth is selective and conservative, exposing or amplifying residual error.
Classy learns interpretable probabilistic rule lists for multiclass classification.
problem Creating interpretable multiclass classifiers that are both accurate and understandable.
method Probabilistic rule lists and minimum description length (MDL) principle for model selection.
result Classy selects small probabilistic rule lists that outperform state-of-the-art classifiers in terms of predictive performance and interpretability.
The power of sparse signal modeling with learned over-complete dictionaries has been demonstrated in a variety of applications and fields, from signal processing to statistical inference and machine learning. However, the statistical properties of these models, such as under-fitting or over-fitting given sets of data, …
A method to distinguish causal from confounded relationships using MDL.
problem Identifying causal relationships from observed variables when there's an unobserved confounding variable.
method Information-theoretic approach based on Kolmogorov complexity and Minimum Description Length (MDL) principle.
result The proposed method, CoCa, effectively distinguishes causal from confounded relationships, even in complex scenarios.
Study improves neural network performance in sequential learning for image classification.
problem Improving neural network performance in sequential learning for image classification.
method Evaluation of approaches for computing prequential description lengths, proposing forward-calibration and replay-streams.
result Improved description lengths for image classification datasets, outperforming previous results.
We consider the fundamental problem of inferring the causal direction between two univariate numeric random variables and from observational data. The two-variable case is especially difficult to solve since it is not possible to use standard conditional independence tests between the variables. To tackle this …
Proposes a new method for finding non-redundant, standout subgroups in numeric datasets.
problem Mining large numbers of redundant subgroups in numeric datasets.
method Dispersion-aware problem formulation based on MDL principle for subgroup set discovery.
result Empirically demonstrates SSD++ returns outstanding subgroup lists.
New method improves bivariate causal discovery by accurately estimating cause variable complexity.
problem Improper estimation of cause variable complexity in current MDL-based methods.
method Rate-distortion MDL (RDMDL) using information dimension for cause variable complexity estimation.
result RDMDL achieves competitive performance on Tübingen dataset.
Paper develops a statistical model for summarizing event sequences.
problem Discovering frequent serial episodes from sequential data.
method Minimum Description Length (MDL) principle with modifications.
result Reduces dictionary size by more than four-fold without losing accuracy.
A new method identifies causal direction using dense functional classes.
problem Determining causal direction between two univariate, continuous-valued variables.
method Minimum Description Length (MDL) principle applied to cubic regression splines.
result LCUBE method achieves superior precision in identifying causal direction.
Robust subgroup discovery finds non-redundant, statistically significant subgroups.
problem Finding interpretable, robust subgroups from data.
method Formulated subgroup lists for univariate and multivariate targets, used MDL principle and greedy heuristic SSD++.
result SSD++ outperforms previous methods in quality and size of subgroup lists.
Regularity Normalization: Neuroscience-Inspired Unsupervised Attention across Neural Network Layerscs.LG
Proposes RN for unsupervised attention in neural networks.
problem Limited, imbalanced, and non-stationary input distributions in various tasks.
method Inspired by neuronal adaptation, RN uses MDL principle and universal code length for incremental layer-wise computation.
result Outperforms existing normalization methods across diverse tasks.
Fast, fully-automated histograms for large data sets.
problem Efficiently constructing histograms for large-scale data.
method G-Enum histograms using Minimum Description Length (MDL) principle for model selection and a greedy search heuristic.
result Construct histograms in linearithmic time, significantly faster than previous methods.
A new objective function for NMF reduces model complexity and improves accuracy.
problem NMF's error-based objective function can lead to overly complex models.
method MDL-NMF uses minimum description length to balance model complexity and accuracy.
result MDL-NMF outperforms traditional NMF on various datasets.
Bridging Algorithmic Information Theory and Machine Learning: A New Approach to Kernel Learningcs.LG
New approach to learning kernels from data using AIT principles.
problem Learning kernels from data in machine learning.
method Sparse Kernel Flows method based on AIT principles.
result Sparse Kernel Flows aligns with MDL principle and offers a robust theoretical foundation.
Determining Principal Component Cardinality through the Principle of Minimum Description Lengthcs.LG
This research simplifies PCA model selection using MDL principle.
problem Choosing the right number of principal components in PCA.
method Reduces NML problems to lower-dimension problems and bounds PCA NML.
result Bound the NML of PCA by terms of the NML of linear regression.
Paper introduces Ddim, a new measure of model complexity, for MDL-based learning and change detection.
problem Characterizing the complexity of probabilistic models for efficient learning and change detection.
method Introduces descriptive dimension (Ddim) as a measure of model complexity. Derives convergence rates and error probabilities for MDL-based learning and change detection.
result Ddim characterizes the performance of MDL-based learning and change detection.
Method generates adversarial examples to improve classifier robustness.
problem Addressing adversarial examples in machine learning.
method MDL principle for generating adversarial examples.
result Evasion rate of 78.24% for adversarial examples compared to 8.16% for original malware.
We analyze MDL for binary classification, quantifying overfitting and underfitting.
problem Understanding the trade-off between underfitting and overfitting in MDL for binary classification.
method Complete characterization of the regularization curve for MDL, extending previous work to all .
result Precise quantitative description of the worst case limiting error as a function of and noise level.
The parametric complexity is the key quantity in the minimum description length (MDL) approach to statistical model selection. Rissanen and others have shown that the parametric complexity of a statistical model approaches a simple function of the Fisher information volume of the model as the sample size goes to in…
Parsimonious module inference in large networksphysics.data-an
We investigate the detectability of modules in large networks when the number of modules is not known in advance. We employ the minimum description length (MDL) principle which seeks to minimize the total amount of information required to describe the network, and avoid overfitting. According to this criterion, we obta…
In recent years there has been an increasing interest in learning Bayesian networks from data. One of the most effective methods for learning such networks is based on the minimum description length (MDL) principle. Previous work has shown that this learning procedure is asymptotically successful: with probability one,…
Compressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theorystat.ML
Study shows LLC correlates with neural network compressibility.
problem Evaluating limits of neural network compression.
method Extended minimum description length principle using singular learning theory.
result Complexity estimates based on LLC are linearly correlated with compressibility.
Paper proves convergence of MDL to Einstein-Hilbert with boundary term.
problem Proving convergence of discrete MDL to continuous Einstein-Hilbert action.
method Proves \(Γ\)-convergence using diffeomorphism-natural discrete MDL-type functional.
result Identifies Carathéodory densities and obtains \(\liminf/\limsup\) bounds.
We introduce a deep, generative autoencoder capable of learning hierarchies of distributed representations from data. Successive deep stochastic hidden layers are equipped with autoregressive connections, which enable the model to be sampled from quickly and exactly via ancestral sampling. We derive an efficient approx…
Proposes a method to adapt DNNs to drift in data distribution.
problem Adapting to out-of-distribution data and shifting objectives.
method Bayesian Inference, Variational Density Propagation, Evidence Lower Bound (ELBO), Minimum Description Length (MDL) Principle.
result Minimizes catastrophic forgetting by approximating MDL principle.
Unified framework for PDF estimation using MDL-based binning and tensor factorization.
problem Challenges in estimating PDFs for non-uniform, multimodal data.
method MDL-based binning with quantile cuts, tensor factorization (CPD).
result Effective PDF estimation on synthetic and real data.
Method infers causal direction using data discretization and complexity calculation.
problem Determining causal direction between continuous variables.
method MDL Binning technique for data discretization and complexity calculation.
result Captures the shape of the data to determine causal direction.
Given data over the joint distribution of two random variables and , we consider the problem of inferring the most likely causal direction between and . In particular, we consider the general case where both and may be univariate or multivariate, and of the same or mixed data types. We take an inf…
Generative model for creating graphs with new communities.
problem Generating graphs with a new community structure.
method Fit Gaussian mixture model to latent space data and add new clusters based on MDL principle.
result Empirically demonstrated effectiveness of GCA for generating graphs with new community structures.
While statistics focusses on hypothesis testing and on estimating (properties of) the true sampling distribution, in machine learning the performance of learning algorithms on future data is the primary issue. In this paper we bridge the gap with a general principle (PHI) that identifies hypotheses with best predictive…
Robust low-rank matrix estimation is a topic of increasing interest, with promising applications in a variety of fields, from computer vision to data mining and recommender systems. Recent theoretical results establish the ability of such data models to recover the true underlying low-rank matrix when a large portion o…
In this paper, we provide a new neural-network based perspective on multi-task learning (MTL) and multi-domain learning (MDL). By introducing the concept of a semantic descriptor, this framework unifies MDL and MTL as well as encompassing various classic and recent MTL/MDL algorithms by interpreting them as different w…
The success of deep learning in numerous application domains created the de- sire to run and train them on mobile devices. This however, conflicts with their computationally, memory and energy intense nature, leading to a growing interest in compression. Recent work by Han et al. (2015a) propose a pipeline that involve…
The Minimum Description Length (MDL) principle states that the optimal model for a given data set is that which compresses it best. Due to practial limitations the model can be restricted to a class such as linear regression models, which we address in this study. As in other formulations such as the LASSO and forward …