让神经网络输出自动满足复杂约束，提升安全性和可靠性。
SnareNet: Flexible Repair Layers for Neural Networks with Hard Constraints
- 添加可微修复层，动态调整输出以满足输入相关的约束条件。
- 在优化学习和轨迹规划任务中，约束满足率更高，目标性能更优。
- 适用于需要严格遵守物理或安全规则的场景，如自动驾驶、工业控制。
神经网络被广泛用作各类领域的快速代理模型，但其无约束输出可能违反物理、操作或安全要求。我们提出 SnareNet，一种可行性可控的架构，用于学习满足输入相关约束的映射。SnareNet 在网络末尾添加一个可微修复层，通过约束空间的像空间进行迭代导航，将输出逐步调整至可行域内，并生成满足用户指定容差的修复输出。通过自适应松弛这一新训练范式，训练初期固定网络初始状态，逐步将其缩小至可行集，实现早期探索与后期严格可行性。在优化学习与轨迹规划基准测试中，SnareNet 始终获得更优的目标质量，且比以往方法更可靠地满足约束，首次在中高精度下稳健地处理非凸约束问题。
原文摘要 · Abstract (English)
Neural networks are increasingly used as fast surrogate models across various domains, but unconstrained predictions can violate physical, operational, or safety requirements. We propose SnareNet, a feasibility-controlled architecture to learn mappings whose outputs must satisfy input-dependent constraints. SnareNet appends a differentiable repair layer that navigates in the constraint map's range space, steering iterates toward feasibility and producing a repaired output that satisfies constraints to a user-specified tolerance. We stabilize end-to-end training by adaptive relaxation, a new training paradigm that snares the neural network at initialization and shrinks it into the feasible set, enabling early exploration and strict feasibility later in training. On optimization learning and trajectory planning benchmarks, SnareNet consistently attains improved objective quality while satisfying constraints more reliably than prior work, and it is the first to enforce non-convex constraints at medium-to-high precision robustly across instances.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。