Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Marcu, Antonia"'
Autor:
Marcu, Antonia
Over the past years, the crucial role of data has largely been shadowed by the field's focus on architectures and training procedures. We often cause changes to the data without being aware of their wider implications. In this paper we show that dist
Externí odkaz:
http://arxiv.org/abs/2211.13734
In this paper we show that the expected generalisation performance of a learning machine is determined by the distribution of risks or equivalently its logarithm -- a quantity we term the risk entropy -- and the fluctuations in a quantity we call the
Externí odkaz:
http://arxiv.org/abs/2202.07350
Autor:
Marcu, Antonia, Prügel-Bennett, Adam
The community lacks theory-informed guidelines for building good data sets. We analyse theoretical directions relating to what aspects of the data matter and conclude that the intuitions derived from the existing literature are incorrect and misleadi
Externí odkaz:
http://arxiv.org/abs/2111.11514
Autor:
Marcu, Antonia, Prügel-Bennett, Adam
Data distortion is commonly applied in vision models during both training (e.g methods like MixUp and CutMix) and evaluation (e.g. shape-texture bias and robustness). This data modification can introduce artificial information. It is often assumed th
Externí odkaz:
http://arxiv.org/abs/2110.13968
Autor:
Harris, Ethan, Marcu, Antonia, Painter, Matthew, Niranjan, Mahesan, Prügel-Bennett, Adam, Hare, Jonathon
Mixed Sample Data Augmentation (MSDA) has received increasing attention in recent years, with many successful variants such as MixUp and CutMix. By studying the mutual information between the function learned by a VAE on the original data and on the
Externí odkaz:
http://arxiv.org/abs/2002.12047
Autor:
Marcu, Antonia, Prügel-Bennett, Adam
In this paper, a new approach to computing the generalisation performance is presented that assumes the distribution of risks, $\rho(r)$, for a learning scenario is known. From this, the expected error of a learning machine using empirical risk minim
Externí odkaz:
http://arxiv.org/abs/1911.04301