SLIDE 1
Active Online Domain Adaptation
Yining Chen (Stanford), Haipeng Luo (USC), Tengyu Ma (Stanford), Chicheng Zhang (University of Arizona)
Domain shift: challenge for ML system
Time
Active Online Domain Adaptation Yining Chen (Stanford) , Haipeng Luo - - PowerPoint PPT Presentation
Active Online Domain Adaptation Yining Chen (Stanford) , Haipeng Luo - - PowerPoint PPT Presentation
Active Online Domain Adaptation Yining Chen (Stanford) , Haipeng Luo (USC), Tengyu Ma (Stanford), Chicheng Zhang (University of Arizona) Domain shift: challenge for ML system Time Online learning: a classical framework for domain shift At
SLIDE 2
SLIDE 3
Online learning: a classical framework for domain shift
- At timestep t = 1, …, T:
- Input
is revealed.
- Learner predicts , suffers some loss.
- Label
is revealed. Expensive!
- > This work: active online learning
Learner can decide whether to query the label.
SLIDE 4
Active online regression: Setup
- Hypothesis class
- Realizable setting:
- At timestep t = 1, …, T:
- is revealed.
- Learner predicts , suffers loss
.
- Learner decides whether to query .
- Metrics: (1) # queries
(2) Regret
- Goal: Minimize R subject to
.
SLIDE 5
Linear regression
- Hypothesis class:
- Prediction strategy:
- Follow the regularized leader on all queried examples till t-1:
- What’s the query strategy?
- Uniformly random queries are optimal without domain structure.
SLIDE 6
Can we do better if the data is structured?
- Domain structure:
- domains
- Domain : support dimension , duration
D1 D2 D1 D2 D3
SLIDE 7
Main contribution: optimal tradeoff with unk unkno nown wn domain structure
- QuFUR (Query in the Face of Uncertainty for Regression):
- Query uncertain examples
- Linear Regression: For any domain partition, with high probability:
- Matching lower bound.
- Generalize to general hypothesis classes w/ bounded Eluder
Dimension.