%0 Generic %1 jiang2019perspective %A Jiang, Hui %D 2019 %K learning %T A New Perspective on Machine Learning: How to do Perfect Supervised Learning %U http://arxiv.org/abs/1901.02046 %X In this work, we introduce the concept of bandlimiting into the theory of machine learning because all physical processes are bandlimited by nature, including real-world machine learning tasks. After the bandlimiting constraint is taken into account, our theoretical analysis has shown that all practical machine learning tasks are asymptotically solvable in a perfect sense. Furthermore, the key towards this solvability almost solely relies on two factors: i) a sufficiently large amount of training samples beyond a threshold determined by a difficulty measurement of the underlying task; ii) a sufficiently complex model that is properly bandlimited. Moreover, for unimodal data distributions, we have derived a new error bound for perfect learning, which can quantify the difficulty of learning. This case-specific bound is much tighter than the uniform bounds in conventional learning theory.

@misc{jiang2019perspective, abstract = {In this work, we introduce the concept of bandlimiting into the theory of machine learning because all physical processes are bandlimited by nature, including real-world machine learning tasks. After the bandlimiting constraint is taken into account, our theoretical analysis has shown that all practical machine learning tasks are asymptotically solvable in a perfect sense. Furthermore, the key towards this solvability almost solely relies on two factors: i) a sufficiently large amount of training samples beyond a threshold determined by a difficulty measurement of the underlying task; ii) a sufficiently complex model that is properly bandlimited. Moreover, for unimodal data distributions, we have derived a new error bound for perfect learning, which can quantify the difficulty of learning. This case-specific bound is much tighter than the uniform bounds in conventional learning theory.}, added-at = {2019-01-09T11:00:38.000+0100}, author = {Jiang, Hui}, biburl = {https://www.bibsonomy.org/bibtex/20e4e7ab99bdf5f184b1b8c37ed3a3c28/stuart10}, description = {A New Perspective on Machine Learning: How to do Perfect Supervised Learning}, interhash = {ef339aaa733f7d1e727fc560fafb8291}, intrahash = {0e4e7ab99bdf5f184b1b8c37ed3a3c28}, keywords = {learning}, note = {cite arxiv:1901.02046Comment: 9 pages}, timestamp = {2019-01-09T11:00:38.000+0100}, title = {A New Perspective on Machine Learning: How to do Perfect Supervised Learning}, url = {http://arxiv.org/abs/1901.02046}, year = 2019 }