Train 'n Trade：参数市场的基础
Train 'n Trade: Foundations of Parameter Markets
AI总结：
本文提出参数市场框架，支持权重交易、交换策略与参数变现，并证明竞争环境下市场参与者相较各自从零训练可实现互惠互利。
摘要：
各组织通常单独训练大型模型。这既昂贵又耗时，尤其是对于大规模基础模型而言。众所周知，这种垂直生产方式是次优的。受这一经济学洞见启发，我们探讨是否有可能通过交易模型中的组成部分（即权重集合）来利用他人的专业知识，仿佛它们是市场商品一样。尽管模型对齐与插值方面的最新进展表明这样做或许可行，但要建立可行的参数市场，必须回答许多基本问题。在本工作中，我们解决了这些基础问题，提出了一个包含市场运行所需基础设施的框架，研究了参数交换策略，并为智能体提供了将参数变现的手段。令人振奋的是，与从头训练孤立模型的智能体相比，我们证明了即使在竞争环境中，也有可能通过使用该市场实现互惠互利。这表明参数市场这一概念可能成为未来改进大规模模型训练的有用范式。
英文摘要：
Organizations typically train large models individually. This is costly and time-consuming, particularly for large-scale foundation models. Such vertical production is known to be suboptimal. Inspired by this economic insight, we ask whether it is possible to leverage others' expertise by trading the constituent parts in models, i.e., sets of weights, as if they were market commodities. While recent advances in aligning and interpolating models suggest that doing so may be possible, a number of fundamental questions must be answered to create viable parameter markets. In this work, we address these basic questions, propose a framework containing the infrastructure necessary for market operations to take place, study strategies for exchanging parameters, and offer means for agents to monetize parameters. Excitingly, compared to agents who train siloed models from scratch, we show that it is possible to mutually gain by using the market, even in competitive settings. This suggests that the notion of parameter markets may be a useful paradigm for improving large-scale model training in the future.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
