论文标题
离线无限宽度基于模型的优化的双向学习
Bidirectional Learning for Offline Infinite-width Model-based Optimization
论文作者
论文摘要
在基于离线模型的优化中,我们仅利用静态设计及其分数来努力最大化黑框目标函数。此问题设置在许多领域都出现,包括材料,机器人,DNA序列和蛋白质的设计。最近的方法在静态数据集上训练深层神经网络(DNN),以充当代理函数,然后对现有设计进行梯度上升,以获得潜在的高分设计。这种方法经常遭受分布外的问题,即代理功能通常会返回差的设计。为了减轻此问题,我们提出了基于离线宽度宽度模型的优化(BDI)的双向学习。 BDI由两个映射组成:正向映射利用静态数据集预测高分设计的得分,而向后映射则利用高分测量设计来预测静态数据集的得分。在先前工作中忽略的向后映射可以将更多信息从静态数据集提取到高分设计中,从而有效地减轻了分布式问题。对于有限宽度的DNN模型,向后映射的损耗函数是棘手的,并且只有近似形式,从而导致设计质量的显着恶化。因此,我们采用了无限宽度的DNN模型,并建议采用相应的神经切线内核来产生封闭形式的损失,以进行更准确的设计更新。各种任务的实验验证了BDI的有效性。该代码可在https://github.com/ggchen1997/bdi上找到。
In offline model-based optimization, we strive to maximize a black-box objective function by only leveraging a static dataset of designs and their scores. This problem setting arises in numerous fields including the design of materials, robots, DNA sequences, and proteins. Recent approaches train a deep neural network (DNN) on the static dataset to act as a proxy function, and then perform gradient ascent on the existing designs to obtain potentially high-scoring designs. This methodology frequently suffers from the out-of-distribution problem where the proxy function often returns poor designs. To mitigate this problem, we propose BiDirectional learning for offline Infinite-width model-based optimization (BDI). BDI consists of two mappings: the forward mapping leverages the static dataset to predict the scores of the high-scoring designs, and the backward mapping leverages the high-scoring designs to predict the scores of the static dataset. The backward mapping, neglected in previous work, can distill more information from the static dataset into the high-scoring designs, which effectively mitigates the out-of-distribution problem. For a finite-width DNN model, the loss function of the backward mapping is intractable and only has an approximate form, which leads to a significant deterioration of the design quality. We thus adopt an infinite-width DNN model, and propose to employ the corresponding neural tangent kernel to yield a closed-form loss for more accurate design updates. Experiments on various tasks verify the effectiveness of BDI. The code is available at https://github.com/GGchen1997/BDI.