Active Online Domain Adaptation

06/25/2020
by   Yining Chen, et al.
9

Online machine learning systems need to adapt to domain shifts. Meanwhile, acquiring label at every timestep is expensive. We propose a surprisingly simple algorithm that adaptively balances its regret and its number of label queries in settings where the data streams are from a mixture of hidden domains. For online linear regression with oblivious adversaries, we provide a tight tradeoff that depends on the durations and dimensionalities of the hidden domains. Our algorithm can adaptively deal with interleaving spans of inputs from different domains. We also generalize our results to non-linear regression for hypothesis classes with bounded eluder dimension and adaptive adversaries. Experiments on synthetic and realistic datasets demonstrate that our algorithm achieves lower regret than uniform queries and greedy queries with equal labeling budget.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/11/2021

Online Continual Adaptation with Active Self-Training

Models trained with offline data often suffer from continual distributio...
research
02/18/2023

Online Instrumental Variable Regression: Regret Analysis and Bandit Feedback

The independence of noise and covariates is a standard assumption in onl...
research
11/02/2021

Stochastic Online Linear Regression: the Forward Algorithm to Replace Ridge

We consider the problem of online linear regression in the stochastic se...
research
10/24/2022

Private Online Prediction from Experts: Separations and Faster Rates

Online prediction from experts is a fundamental problem in machine learn...
research
02/16/2021

Smoothed Analysis with Adaptive Adversaries

We prove novel algorithmic guarantees for several online problems in the...
research
04/14/2023

Robust Algorithms on Adaptive Inputs from Bounded Adversaries

We study dynamic algorithms robust to adaptive input generated from sour...
research
07/03/2023

Adaptive Principal Component Regression with Applications to Panel Data

Principal component regression (PCR) is a popular technique for fixed-de...

Please sign up or login with your details

Forgot password? Click here to reset