Normalized Online Learning
This addresses a practical issue for machine learning practitioners by making online learning more efficient and robust, though it appears incremental as it builds on existing online learning frameworks.
The paper tackles the problem of feature scale sensitivity in online learning algorithms by introducing scale-independent methods that eliminate the need for data pre-normalization. The result is proven regret bounds dependent on scale ratios rather than absolute scales, reducing test-time and test-space complexity while improving robustness.
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.