Skip to search formSkip to main contentSkip to account menu

When can unlabeled data improve the learning rate?

This work argues that for improvements in the minimax learning rate to be realistic and indisputable, certain specific conditions should be satisfied and previous analyses have failed to meet those conditions.
View PDF on arXiv (opens in a new tab)

Differential privacy for learning vector quantization

View via Publisher (opens in a new tab)

Statistical Mechanics of On-Line Learning Under Concept Drift

A modeling framework for the investigation of on-line machine learning processes in non-stationary environments is introduced and it is shown that LVQ is capable of tracking a classification scheme under drift to a non-trivial extent and that concept drift can cause the persistence of sub-optimal plateau states in gradient based training of layered neural networks for regression.
View PDF (opens in a new tab)

Time Series Prediction for Graphs in Kernel and Dissimilarity Spaces

It is found that simple regression methods, such as kernel regression, are sufficient to capture the dynamics in the theoretical models, but that Gaussian process regression significantly improves the prediction error for real-world data.
View on Springer (opens in a new tab)

Interpretation of linear classifiers by means of feature relevance bounds

View via Publisher (opens in a new tab)

Prototype-based classifiers in the presence of concept drift: A modelling framework

First results demonstrate that, while basic LVQ algorithms are suitable for the training in non-stationary environments, weight decay as an explicit mechanism of forgetting does not improve the performance under the considered drift processes.
View PDF on arXiv (opens in a new tab)

Feature Relevance Bounds for Linear Classification

This work addresses the important case of linear classifiers and transfers the problem how to infer feature relevance bounds to a convex optimization problem and demonstrates the superiority of the resulting technique in comparison to popular feature-relevance determination methods in several benchmarks.
View Paper (opens in a new tab)

FRI-Feature Relevance Intervals for Interpretable and Interactive Data Exploration

FRI is an open source Python library that can be used to identify all-relevant variables in linear classification and (ordinal) regression problems and is able to provide the base for further general experimentation or in specific can facilitate the search for alternative biomarkers.
View on IEEE (opens in a new tab)

Convergence of Multi-pass Large Margin Nearest Neighbor Metric Learning

It is shown that an iterated LMNN scheme (multi-pass LMNN) is a valid optimization technique for the original LMNN cost function without the assumption that the nearest neighbors within classes remain constant.
View via Publisher (opens in a new tab)

Supervised learning in the presence of concept drift: a modelling framework

Two example types of learning systems are model: prototype-based learning vector quantization (LVQ) for classification and shallow, layered neural networks for regression tasks, and so-called student–teacher scenarios in which the systems are trained from a stream of high-dimensional, labeled data.
View on Springer (opens in a new tab)
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)