paper-with-me

홈 › Papers

Minimal Achievable Sufficient Statistic Learning

2019-05-19 · Milan Cvitkovic, Günther Koliander

We introduce Minimal Achievable Sufficient Statistic (MASS) Learning, a training method for machine learning models that attempts to produce minimal sufficient statistics with respect to a class of functions (e.g. deep networks) being optimized over. In deriving MASS Learning, we also introduce Conserved Differential Information (CDI), an information-theoretic quantity that - unlike standard mutual information - can be usefully applied to deterministically-dependent continuous random variables like the input and output of a deep network. In a series of experiments, we show that deep networks trained with MASS Learning achieve competitive performance on supervised learning and uncertainty quantification benchmarks.

📄 PDF Abstract BibTeX arXiv:1905.07822

Code (1)

mwcvitkovic/MASS-Learning 공식 구현 pytorch

Tasks

BIG-bench Machine LearningUncertainty Quantification

Similar Papers 제목 키워드 기반

Trimming the Independent Fat: Sufficient Statistics, Mutual Information, and Predictability from Effective Channel States

2017-02-07 · Ryan G. James, John R. Mahoney, James P. Crutchfield

One of the most fundamental questions one can ask about a pair of random variables X and Y is the value of their mutual information. Unfortunately, this task is often stymied by the extremely large dimension of the varia…

Minimal Sufficient Representations for Self-interpretable Deep Neural Networks

2026-03-25 · Zhiyao Tan, Liu Li, Huazhen Lin arxiv

Deep neural networks (DNNs) achieve remarkable predictive performance but remain difficult to interpret, largely due to overparameterization that obscures the minimal structure required for interpretation. Here we introd…

Representation Learning

Preisach Attention: A Hysteretic Model of Sequential Memory

2026-05-22 · Piotr Frydrych arxiv

We introduce the Preisach Attention Layer (PAL), a novel sequence modelling architecture grounded in the classical Preisach hysteresis operator from mathematical physics. PAL replaces the softmax attention mechanism with…

Computational lower bounds in latent models: clustering, sparse-clustering, biclustering

2025-06-16 · Bertrand Even, Christophe Giraud, Nicolas Verzelen

In many high-dimensional problems, like sparse-PCA, planted clique, or clustering, the best known algorithms with polynomial time complexity fail to reach the statistical performance provably achievable by algorithms fre…

Clustering

The Extremum Stack is a Minimal Sufficient Statistic for Rate-Independent Functionals: A Kolmogorov Complexity Characterisation

2026-05-16 · Piotr Frydrych arxiv

We prove that the extremum stack of a discrete sequence is a minimal sufficient statistic for the class of all computable, causal, rate-independent functionals, in the sense of Kolmogorov complexity. Specifically, we est…