paper-with-me

홈 › Papers

Nearly Maximally Predictive Features and Their Dimensions

2017-02-27 · Sarah E. Marzen, James P. Crutchfield

Scientific explanation often requires inferring maximally predictive features from a given data set. Unfortunately, the collection of minimal maximally predictive features for most stochastic processes is uncountably infinite. In such cases, one compromises and instead seeks nearly maximally predictive features. Here, we derive upper-bounds on the rates at which the number and the coding cost of nearly maximally predictive features scales with desired predictive power. The rates are determined by the fractal dimensions of a process' mixed-state distribution. These results, in turn, show how widely-used finite-order Markov models can fail as predictors and that mixed-state predictive features offer a substantial improvement.

📄 PDF Abstract BibTeX arXiv:1702.08565

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Transparency, Auditability and eXplainability of Machine Learning Models in Credit Scoring

2020-09-28 · Michael Bücker, Gero Szepannek, Alicja Gosiewska, Przemyslaw Biecek

A major requirement for credit scoring models is to provide a maximally accurate risk prediction. Additionally, regulators demand these models to be transparent and auditable. Thus, in credit scoring, very simple predict…

BIG-bench Machine Learning

Least Informative Dimensions

2013-12-01 · NeurIPS 2013 12 · Fabian Sinz, Anna Stockl, Jan Grewe, Jan Benda

We present a novel non-parametric method for finding a subspace of stimulus features that contains all information about the response of a system. Our method generalizes similar approaches to this problem such as spike t…

The equivalence of information-theoretic and likelihood-based methods for neural dimensionality reduction

2015-02-24

Stimulus dimensionality-reduction methods in neuroscience seek to identify a low-dimensional space of stimulus features that affect a neuron's probability of spiking. One popular method, known as maximally informative di…

Dimensionality Reduction

Vanilla Feature Distillation for Improving the Accuracy-Robustness Trade-Off in Adversarial Training

2022-06-05 · Guodong Cao, Zhibo Wang, Xiaowei Dong, Zhifei Zhang 외

Adversarial training has been widely explored for mitigating attacks against deep models. However, most existing works are still trapped in the dilemma between higher accuracy and stronger robustness since they tend to f…

Knowledge Distillation

An Aggregation Method for Sparse Logistic Regression

2014-10-25 · Zhe Liu

$L_1$ regularized logistic regression has now become a workhorse of data mining and bioinformatics: it is widely used for many classification problems, particularly ones with many features. However, $L_1$ regularization …

General Classificationregression