Normalized Online Learning
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Aug 2014.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 2; 2022: 1; 2023: 0; 2024: 1; 2025: 1; 2026: 2.
7 papers.
- 2021Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discriminationcited by 53
- 2022Scale-free Unconstrained Online Learning for Curved Lossescited by 13
- 2021Dynamic Regret for Strongly Adaptive Methods and Optimality of Online KRRcited by 4
- 2024Online Learning under Haphazard Input Conditions: A Comprehensive Review and Analysiscited by 2
- 2026Optimal Regret for Policy Optimization in Contextual Banditscited by 1
- 2026Scale-free adaptive planning for deterministic dynamics & discounted rewardscited by 1
- 2025Comparing Normalization Methods for Portfolio Optimization with Reinforcement Learningcited by 0
- 2026Scale-free adaptive planning for deterministic dynamics & discounted rewards20 Apr 2026
- 2026Optimal Regret for Policy Optimization in Contextual Bandits14 Feb 2026
- 2025Comparing Normalization Methods for Portfolio Optimization with Reinforcement Learning5 Aug 2025
- 2024Online Learning under Haphazard Input Conditions: A Comprehensive Review and Analysis7 Apr 2024
- 2022Scale-free Unconstrained Online Learning for Curved Losses11 Feb 2022
- 2021Dynamic Regret for Strongly Adaptive Methods and Optimality of Online KRR22 Nov 2021
- 2021Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination5 Jul 2021