Training Binary Neural Networks using the Bayesian Learning Rule
This work provides a principled justification for existing methods in training binary neural networks, which are computation-efficient and hardware-friendly, addressing a domain-specific problem in machine learning.
The paper tackles the challenge of training binary neural networks, which involve discrete optimization, by proposing a principled approach using the Bayesian learning rule, resulting in state-of-the-art performance and enabling uncertainty estimation for continual learning to avoid catastrophic forgetting.
Neural networks with binary weights are computation-efficient and hardware-friendly, but their training is challenging because it involves a discrete optimization problem. Surprisingly, ignoring the discrete nature of the problem and using gradient-based methods, such as the Straight-Through Estimator, still works well in practice. This raises the question: are there principled approaches which justify such methods? In this paper, we propose such an approach using the Bayesian learning rule. The rule, when applied to estimate a Bernoulli distribution over the binary weights, results in an algorithm which justifies some of the algorithmic choices made by the previous approaches. The algorithm not only obtains state-of-the-art performance, but also enables uncertainty estimation for continual learning to avoid catastrophic forgetting. Our work provides a principled approach for training binary neural networks which justifies and extends existing approaches.