Geometric Median

The geometric median (GM) is a robust measure of central tendency, minimizing the sum of distances to data points, offering advantages over the mean in the presence of outliers or noise. Current research focuses on developing efficient and private algorithms for computing the GM, particularly within the context of high-dimensional data and large datasets, with applications ranging from robust data pruning and clustering to reinforcement learning and face detection. These advancements are improving the accuracy and efficiency of various machine learning tasks while addressing challenges related to data privacy and computational scalability.