Compression Aware Certified Training
This addresses the need for efficient and robust models in safety-critical applications, representing a novel integration rather than an incremental improvement.
The paper tackles the problem of balancing efficiency and robustness in deep neural networks for safety-critical, resource-constrained environments by proposing CACTUS, a framework that unifies compression and certified robustness during training, achieving state-of-the-art accuracy and certified performance for pruning and quantization across various datasets.
Deep neural networks deployed in safety-critical, resource-constrained environments must balance efficiency and robustness. Existing methods treat compression and certified robustness as separate goals, compromising either efficiency or safety. We propose CACTUS (Compression Aware Certified Training Using network Sets), a general framework for unifying these objectives during training. CACTUS models maintain high certified accuracy even when compressed. We apply CACTUS for both pruning and quantization and show that it effectively trains models which can be efficiently compressed while maintaining high accuracy and certifiable robustness. CACTUS achieves state-of-the-art accuracy and certified performance for both pruning and quantization on a variety of datasets and input specifications.