Energy-Efficient ML

Energy-efficient machine learning studies how to reduce the resources required to train and run models, especially on edge devices and at large serving scale. Common approaches include pruning, quantization, distillation, sparse and early-exit models, efficient scheduling and routing, and hardware-software co-design for GPUs, accelerators, and neuromorphic chips. Researchers increasingly measure energy on real hardware and assess carbon and other environmental impacts across the model life cycle, since proxies such as FLOPs do not reliably predict deployment costs. The central challenge is balancing energy, accuracy, latency, and memory while determining whether efficiency gains translate into lower total impact as usage grows.