提出自修改权重的元学习算法，解决长时序训练稳定性问题。
Greedy dynamical meta-learning
- 内环自我优化高维参数，外环低维元优化调整策略。
- 外环用零阶优化，仅需少量参数，适合任意时长训练。
- 适用于大模型长期学习，提升训练稳定性和效率。
梯度下降在大规模模型上表现良好，但在长时间跨度下变得不稳定；无梯度优化器虽可适应任意时间跨度，却受限于高维空间。由于大模型的学习过程持续时间长，现有方法难以有效加速学习。为此，我们提出一种元学习算法，让智能体自主学习如何修改自身的权重和偏置。该算法包含两个循环：内环中，智能体对自身进行高维优化；外环中，我们对内环进行低维优化。由于外环仅涉及极少数参数，可采用标准的零阶优化方法。
原文摘要 · Abstract (English)
Gradient descent scales well to large models, but becomes unstable over long time horizons. Gradient-free optimizers can scale to arbitrary timespans, but are hobbled by high dimensions. Since learning occurs in large models over long timescales, neither of these approaches is likely to produce traits which can accelerate the learning process. Instead, we propose a meta-learning algorithm in which the agent learns to modify its own weights and biases. Our algorithm consists of an inner loop, wherein the agent performs some high-dimensional optimization upon itself, and an outer loop, wherein we perform some low-dimensional optimization upon the inner loop. Since the outer loop handles very few parameters, standard zeroth-order methods may be used.
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。