HiReLC: Hierarchical Reinforcement Learning for Neural Network Compression (Pruning and Quantization)

arXiv·medium signal

HiReLC is a hierarchical ensemble reinforcement-learning framework that automates joint pruning and quantization for neural network compression, framing compression as a hierarchical RL search over those decisions. Kamar Hibatallah Baghdadi and colleagues target automated efficiency optimization without manual tuning. Practical for practitioners squeezing models down for efficient inference.