Normalized Online Learning
This work addresses a practical issue for machine learning practitioners by making online learning more robust and efficient, though it appears incremental as it builds on existing online learning methods.
The paper tackles the problem of feature scale sensitivity in online learning by introducing algorithms with regret bounds dependent on the ratio of scales in the data, eliminating the need for pre-normalization and reducing test-time and test-space complexity.
We introduce online learning algorithms which are independent of feature scales, proving regret bounds dependent on the ratio of scales existent in the data rather than the absolute scale. This has several useful effects: there is no need to pre-normalize data, the test-time and test-space complexity are reduced, and the algorithms are more robust.