paper-with-me

홈 › Papers

Learning under Singularity: An Information Criterion improving WBIC and sBIC

2024-02-20 · Lirui Liu, Joe Suzuki

We introduce a novel Information Criterion (IC), termed Learning under Singularity (LS), designed to enhance the functionality of the Widely Applicable Bayes Information Criterion (WBIC) and the Singular Bayesian Information Criterion (sBIC). LS is effective without regularity constraints and demonstrates stability. Watanabe defined a statistical model or a learning machine as regular if the mapping from a parameter to a probability distribution is one-to-one and its Fisher information matrix is positive definite. In contrast, models not meeting these conditions are termed singular. Over the past decade, several information criteria for singular cases have been proposed, including WBIC and sBIC. WBIC is applicable in non-regular scenarios but faces challenges with large sample sizes and redundant estimation of known learning coefficients. Conversely, sBIC is limited in its broader application due to its dependence on maximum likelihood estimates. LS addresses these limitations by enhancing the utility of both WBIC and sBIC. It incorporates the empirical loss from the Widely Applicable Information Criterion (WAIC) to represent the goodness of fit to the statistical model, along with a penalty term similar to that of sBIC. This approach offers a flexible and robust method for model selection, free from regularity constraints.

📄 PDF Abstract BibTeX arXiv:2402.12762

Code (0)

등록된 구현이 없습니다.

Tasks

Model Selection

Similar Papers 제목 키워드 기반

Estimating Real Log Canonical Thresholds

2019-06-04 · Toru Imai

Evaluation of the marginal likelihood plays an important role in model selection problems. The widely applicable Bayesian information criterion (WBIC) and singular Bayesian information criterion (sBIC) give approximation…

Model Selection

An Asymptotic Equation Linking WAIC and WBIC in Singular Models

2025-05-20 · Naoki Hayashi, Takuro Kutsuna, Sawa Takamuku

In statistical learning, models are classified as regular or singular depending on whether the mapping from parameters to probability distributions is injective. Most models with hierarchical structures or latent variabl…

Computational EfficiencyLearning TheoryModel Selection

Choosing the Number of Topics in LDA Models -- A Monte Carlo Comparison of Selection Criteria

2022-12-28 · Victor Bystrov, Viktoriia Naboka, Anna Staszewska-Bystrova, Peter Winker

Selecting the number of topics in LDA models is considered to be a difficult task, for which alternative approaches have been proposed. The performance of the recently developed singular Bayesian information criterion (s…

Model Selection

Empirical Similarity for Absent Data Generation in Imbalanced Classification

2015-08-05 · Arash Pourhabib

When the training data in a two-class classification problem is overwhelmed by one class, most classification techniques fail to correctly identify the data points belonging to the underrepresented class. We propose Simi…

ClassificationGeneral Classificationimbalanced classificationSynthetic Data Generation

Streaming Bayesian Inference for Crowdsourced Classification

2019-11-13 · NeurIPS 2019 12 · Edoardo Manino, Long Tran-Thanh, Nicholas R. Jennings

A key challenge in crowdsourcing is inferring the ground truth from noisy and unreliable data. To do so, existing approaches rely on collecting redundant information from the crowd, and aggregating it with some probabili…

Bayesian InferenceBinary ClassificationClassificationGeneral Classification