HERO: Hessian-Enhanced Robust Optimization for Unifying and Improving Generalization and Quantization Performance
This addresses the need for efficient deployment of models on mobile and edge devices by enhancing both generalization and quantization robustness, representing a novel method for a known bottleneck.
The paper tackles the problem of improving neural network generalization and quantization performance simultaneously by proposing HERO, a Hessian-enhanced robust optimization method, which achieves up to a 3.8% gain in test accuracy and over 10% accuracy improvement in post-training quantization over SGD-trained models.
With the recent demand of deploying neural network models on mobile and edge devices, it is desired to improve the model's generalizability on unseen testing data, as well as enhance the model's robustness under fixed-point quantization for efficient deployment. Minimizing the training loss, however, provides few guarantees on the generalization and quantization performance. In this work, we fulfill the need of improving generalization and quantization performance simultaneously by theoretically unifying them under the framework of improving the model's robustness against bounded weight perturbation and minimizing the eigenvalues of the Hessian matrix with respect to model weights. We therefore propose HERO, a Hessian-enhanced robust optimization method, to minimize the Hessian eigenvalues through a gradient-based training process, simultaneously improving the generalization and quantization performance. HERO enables up to a 3.8% gain on test accuracy, up to 30% higher accuracy under 80% training label perturbation, and the best post-training quantization accuracy across a wide range of precision, including a >10% accuracy improvement over SGD-trained models for common model architectures on various datasets.