2025/01/26 by Li Ai, Tengzhou No. Middle School, AI, Lumen +13
Computer Science · #Embedded Systems Design Techniques #FOS: Computer and information sciences #Machine Learning (cs.LG) #Parallel Computing and Optimization Techniques #Real-Time Systems Scheduling
paper · pdf · doi:10.48550/arxiv.2501.16394
openalex publication_date 2025/01/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Addressing the resource waste caused by fixed computation paradigms in deep learning models under dynamic scenarios, this paper proposes a Transformer-1 architecture based on the principle of deep adaptivity. This architecture achieves dynamic matching between input features and computational resources by establishing a joint optimization model for complexity and computation. Our core contributions include: (1) designing a two-layer control mechanism, composed of a complexity predictor and a reinforcement learning policy network, enabling end-to-end optimization of computation paths; (2) deriving a lower bound theory for dynamic computation, proving the system's theoretical reach to optimal efficiency; and (3) proposing a layer folding technique and a CUDA Graph pre-compilation scheme, overcoming the engineering bottlenecks of dynamic architectures. In the ImageNet-1K benchmark test, our method reduces FLOPs by 42.7% and peak memory usage by 34.1% compared to the standard Transformer, while maintaining comparable accuracy (±0.3%). Furthermore, we conducted practical deployment on the Jetson AGX Xavier platform, verifying the effectiveness and practical value of this method in resource-constrained environments. To further validate the generality of the method, we also conducted experiments on several natural language processing tasks and achieved significant improvements in resource efficiency.