Regret in online learning - Cross Validated
In online learning/online convex optimization, it's often the case that you compare your algorithm against the best action in hindsight (i.e., from https://people.cs.umass.edu/~akshay/courses/cs690m/
Regret in online learning - Cross Validated Stack Internal Knowledge at work Bring the best of human thought and AI automation together at your work. Explore Stack Internal Regret in online learning Ask Question Asked 7 years, 6 months ago Modified 6 years, 3 months ago Viewed 4k times 4 $\begingroup$ In online learning/online convex optimization, it's often the case that you compare your algorithm against the best action in hindsight (i.e., from https://people.cs.umass.edu/~akshay/courses/cs690m/files/lec15.pdf ) $$ \operatorname{Regret}(T)=\sum_t{f_t(w_t)}-\min_u \sum_t{f_t(u)} $$ For sequen
related reading
- Yes you should understand backprop | by Andrej Karpathy | Mediumkarpathy.medium.com
- Online Learning: A Comprehensive Surveyarxiv.org
- Why Momentum Really Worksdistill.pub
- 1011.0686arxiv.org
- Part 3: Intro to Policy Optimization - Spinning Up documentationspinningup.openai.com
- Real-time machine learning: challenges and solutionshuyenchip.com
- ML Mentorship: Some Q/A about RLevjang.com
- 16831_lecture09_beckart.pdfcs.cmu.edu
- An overview of gradient descent optimization algorithmsruder.io
- [2506.22401] Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RLarxiv.org
- CS 285: Lecture 13, Part 2youtube.com
- CS231n Deep Learning for Computer Visioncs231n.github.io