用字典退火学习近似最近邻搜索的更好编码
Learning Better Encoding for Approximate Nearest Neighbor Search with Dictionary Annealing
摘要：
我们介绍了一种新的字典优化方法，用于近似最近邻（ANN）搜索的高维矢量量化。矢量量化方法首先寻找一系列字典，然后通过从这些字典中选择的元素的和来近似每个矢量。一个最佳的字典系列应该是相互独立的，每个字典应该为目标数据集生成一个平衡的编码。现有的方法没有明确考虑到这一点。为了实现这些目标以及最小化的量化误差（残留），我们提出了一种新的字典优化方法称为\emph{Dictionary Annealing}，交替“加热”一个单一的字典通过生成一个中间数据集与残留向量，“冷却”的字典通过拟合中间数据集，然后提取新的残留向量的下一次迭代。更好的代码可以通过DA学习用于ANN搜索任务。DA很容易在GPU上实现，以利用最新的计算技术，并可以很容易地扩展到在线字典学习计划。我们通过实验表明，我们的优化字典大大降低了整体量化误差。结合残差矢量量化，我们优化的字典导致一个更好的近似最近邻搜索性能相比，国家的最先进的方法。
英文摘要：
We introduce a novel dictionary optimization method for high-dimensional vector quantization employed in approximate nearest neighbor (ANN) search. Vector quantization methods first seek a series of dictionaries, then approximate each vector by a sum of elements selected from these dictionaries. An optimal series of dictionaries should be mutually independent, and each dictionary should generate a balanced encoding for the target dataset. Existing methods did not explicitly consider this. To achieve these goals along with minimizing the quantization error (residue), we propose a novel dictionary optimization method called \emph{Dictionary Annealing} that alternatively "heats up" a single dictionary by generating an intermediate dataset with residual vectors, "cools down" the dictionary by fitting the intermediate dataset, then extracts the new residual vectors for the next iteration. Better codes can be learned by DA for the ANN search tasks. DA is easily implemented on GPU to utilize the latest computing technology, and can easily extended to an online dictionary learning scheme. We show by experiments that our optimized dictionaries substantially reduce the overall quantization error. Jointly used with residual vector quantization, our optimized dictionaries lead to a better approximate nearest neighbor search performance compared to the state-of-the-art methods.
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。
