Online Learning in Contextual Bandits using Gated Linear Networks
This addresses the need for efficient online algorithms in contextual bandits, offering a competitive solution with theoretical backing, though it is incremental as it builds on existing Gated Linear Networks.
The paper tackled the problem of online learning in contextual bandits by introducing Gated Linear Contextual Bandits (GLCB), which achieved median first-place performance compared to 9 state-of-the-art deep learning algorithms on standard benchmarks.
We introduce a new and completely online contextual bandit algorithm called Gated Linear Contextual Bandits (GLCB). This algorithm is based on Gated Linear Networks (GLNs), a recently introduced deep learning architecture with properties well-suited to the online setting. Leveraging data-dependent gating properties of the GLN we are able to estimate prediction uncertainty with effectively zero algorithmic overhead. We empirically evaluate GLCB compared to 9 state-of-the-art algorithms that leverage deep neural networks, on a standard benchmark suite of discrete and continuous contextual bandit problems. GLCB obtains median first-place despite being the only online method, and we further support these results with a theoretical study of its convergence properties.