Zobrazeno 1 - 10
of 30
pro vyhledávání: '"Mey, Alexander"'
Autor:
Mey, Alexander, Castro, Rui Manuel
We consider the task of identifying the causal parents of a target variable among a set of candidates from observational data. Our main assumption is that the candidate variables are observed in different environments which may, under certain assumpt
Externí odkaz:
http://arxiv.org/abs/2401.05218
Sequential decision making techniques hold great promise to improve the performance of many real-world systems, but computational complexity hampers their principled application. Influence-based abstraction aims to gain leverage by modeling local sub
Externí odkaz:
http://arxiv.org/abs/2011.01788
Autor:
Mey, Alexander
Statistical machine learning theory often tries to give generalization guarantees of machine learning models. Those models naturally underlie some fluctuation, as they are based on a data sample. If we were unlucky, and gathered a sample that is not
Externí odkaz:
http://arxiv.org/abs/2010.02576
In their thought-provoking paper [1], Belkin et al. illustrate and discuss the shape of risk curves in the context of modern high-complexity learners. Given a fixed training sample size $n$, such curves show the risk of a learner as a function of som
Externí odkaz:
http://arxiv.org/abs/2004.04328
Learning performance can show non-monotonic behavior. That is, more data does not necessarily lead to better models, even on average. We propose three algorithms that take a supervised learning model and make it perform more monotone. We prove consis
Externí odkaz:
http://arxiv.org/abs/1911.11030
Autor:
Mey, Alexander, Loog, Marco
In this work we investigate to which extent one can recover class probabilities within the empirical risk minimization (ERM) paradigm. The main aim of our paper is to extend existing results and emphasize the tight relations between empirical risk mi
Externí odkaz:
http://arxiv.org/abs/1908.11823
Autor:
Mey, Alexander, Loog, Marco
Semi-supervised learning is a setting in which one has labeled and unlabeled data available. In this survey we explore different types of theoretical results when one uses unlabeled data in classification and regression tasks. Most methods that use u
Externí odkaz:
http://arxiv.org/abs/1908.09574
Plotting a learner's average performance against the number of training samples results in a learning curve. Studying such curves on one or more data sets is a way to get to a better understanding of the generalization properties of this learner. The
Externí odkaz:
http://arxiv.org/abs/1907.05476
Manifold regularization is a commonly used technique in semi-supervised learning. It enforces the classification rule to be smooth with respect to the data-manifold. Here, we derive sample complexity bounds based on pseudo-dimension for models that a
Externí odkaz:
http://arxiv.org/abs/1906.06100
While the success of semi-supervised learning (SSL) is still not fully understood, Sch\"olkopf et al. (2012) have established a link to the principle of independent causal mechanisms. They conclude that SSL should be impossible when predicting a targ
Externí odkaz:
http://arxiv.org/abs/1905.12081