Online Limited Memory Neural-Linear Bandits with Likelihood Matching
arXiv:2102.03799
Abstract
We study neural-linear bandits for solving problems where {\em both} exploration and representation learning play an important role. Neural-linear bandits harnesses the representation power of Deep Neural Networks (DNNs) and combines it with efficient exploration mechanisms by leveraging uncertainty estimation of the model, designed for linear contextual bandits on top of the last hidden layer. In order to mitigate the problem of representation change during the process, new uncertainty estimations are computed using stored data from an unlimited buffer. Nevertheless, when the amount of stored data is limited, a phenomenon called catastrophic forgetting emerges. To alleviate this, we propose a likelihood matching algorithm that is resilient to catastrophic forgetting and is completely online. We applied our algorithm, Limited Memory Neural-Linear with Likelihood Matching (NeuralLinear-LiM2) on a variety of datasets and observed that our algorithm achieves comparable performance to the unlimited memory approach while exhibits resilience to catastrophic forgetting.
arXiv commentICML 2021. arXiv admin note: text overlap with arXiv:1901.08612
References in corpus (12)
- Overcoming catastrophic forgetting in neural networks
- A Contextual-Bandit Approach to Personalized News Article Recommendation
- Neural Tangent Kernel: Convergence and Generalization in Neural Networks
- Thompson Sampling for Contextual Bandits with Linear Payoffs
- Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning
- VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning
- Neural Contextual Bandits with UCB-based Exploration
- Every Model Learned by Gradient Descent Is Approximately a Kernel Machine
- Neural Thompson Sampling
- Shallow Updates for Deep Reinforcement Learning
- Neural Contextual Bandits with Deep Representation and Shallow Exploration
- Is a picture worth a thousand words? A Deep Multi-Modal Fusion Architecture for Product Classification in e-commerce