🏢 Forschungszentrum Jülich & RWTH Aachen
Optimizing Automatic Differentiation with Deep Reinforcement Learning
·2461 words·12 mins·
loading
·
loading
Reinforcement Learning
🏢 Forschungszentrum Jülich & RWTH Aachen
Deep reinforcement learning optimizes automatic differentiation, achieving up to 33% improvement in Jacobian computation by finding efficient elimination orders.