Boosting Classifiers with Noisy Inference
This work addresses a practical issue for deploying boosting algorithms in noisy environments, such as communication or computation substrates, but it is incremental as it builds on existing boosting methods.
The paper tackles the problem of performance degradation in boosting classifiers when base classifier outputs are noisy, showing that allocating more resources to important base classifiers effectively reduces this degradation. The optimized noisy boosting classifiers are demonstrated to be more robust than bagging during inference, with numerical evidence supporting the benefits.
We present a principled framework to address resource allocation for realizing boosting algorithms on substrates with communication or computation noise. Boosting classifiers (e.g., AdaBoost) make a final decision via a weighted vote from the outputs of many base classifiers (weak classifiers). Suppose that the base classifiers' outputs are noisy or communicated over noisy channels; these noisy outputs will degrade the final classification accuracy. We show that this degradation can be effectively reduced by allocating more system resources for more important base classifiers. We formulate resource optimization problems in terms of importance metrics for boosting. Moreover, we show that the optimized noisy boosting classifiers can be more robust than bagging for the noise during inference (test stage). We provide numerical evidence to demonstrate the benefits of our approach.