Metric learning is an important area of machine learning, in which a similarity measure between sets of objects is learned from data. In a modern context, this data may come from crowd-sourcing problem instances to a set of users (or workers), who are likely to have different abilities and levels of commitment to the task. In this thesis, we first try to look over some of the main methods developed in this field of machine learning. Finally, we present a mechanism design approach for incentivizing workers to produce accurate data for a metric learning task. We show how to incorporate the data provided using this mechanism into a metric learning algorithm, and establish the theoretical properties of this approach. Results on some simulated p...
Many machine learning methods, such as the k-nearest neighbours algorithm, heavily depend on the dis...
Many algorithms rely critically on being given a good metric over their inputs. For instance, data c...
Many important machine learning and data mining algorithms rely on a measure to provide a notion of ...
Many Machine Learning algorithms make use of a notion of distance or similarity between examples to ...
International audienceSimilarity between objects plays an important role in both human cognitive pro...
Many algorithms rely critically on being given a good metric over their inputs. For instance, data ...
The need for appropriate ways to measure the distance or similarity between data is ubiquitous in ma...
A key component of any reinforcement learning algorithm is the underlying representation used by the...
In this paper, we wanted to compare distance metric-learning algorithms on UCI datasets. We wanted t...
Much like in other modeling disciplines does the distance metric used (a measure for dissimilarity) ...
L'apprentissage automatique concerne l'apprentissage de modèles prédictifs à partir de donnée. Pour ...
Metric learning aims to learn a distance metric such that semantically similar instances are pulled ...
A typical machine learning algorithm takes advantage of training data to discover patterns among obs...
International audienceThis paper introduces a novel distance metric learning framework. Working with...
Abstract Distance metric plays an important role in machine learning which is crucial to the perform...
Many machine learning methods, such as the k-nearest neighbours algorithm, heavily depend on the dis...
Many algorithms rely critically on being given a good metric over their inputs. For instance, data c...
Many important machine learning and data mining algorithms rely on a measure to provide a notion of ...
Many Machine Learning algorithms make use of a notion of distance or similarity between examples to ...
International audienceSimilarity between objects plays an important role in both human cognitive pro...
Many algorithms rely critically on being given a good metric over their inputs. For instance, data ...
The need for appropriate ways to measure the distance or similarity between data is ubiquitous in ma...
A key component of any reinforcement learning algorithm is the underlying representation used by the...
In this paper, we wanted to compare distance metric-learning algorithms on UCI datasets. We wanted t...
Much like in other modeling disciplines does the distance metric used (a measure for dissimilarity) ...
L'apprentissage automatique concerne l'apprentissage de modèles prédictifs à partir de donnée. Pour ...
Metric learning aims to learn a distance metric such that semantically similar instances are pulled ...
A typical machine learning algorithm takes advantage of training data to discover patterns among obs...
International audienceThis paper introduces a novel distance metric learning framework. Working with...
Abstract Distance metric plays an important role in machine learning which is crucial to the perform...
Many machine learning methods, such as the k-nearest neighbours algorithm, heavily depend on the dis...
Many algorithms rely critically on being given a good metric over their inputs. For instance, data c...
Many important machine learning and data mining algorithms rely on a measure to provide a notion of ...