In this paper we are concerned with localizing the change points in a high-dimensional BTL model with piece-wise constant parameters.

Pretraining on large unlabeled datasets has been proven to improve the downstream task performance on many computer vision tasks, such as 2D object detection and video classification. However, for large-scale 3D scenes, such as outdoor LiDAR point clouds, pretraining is not widely used. Due to the special data characteristics of large 3D point clouds, approaches for 2D pretraining frameworks tend to not generalize well to this domain. In this paper, we propose a new self-supervised pretraining method that targets large-scale 3D scenes. We pretrain commonly used point-based and voxel-based model architectures and show the transfer learning performance on 3D object detection and semantic segmentation. We demonstrate the effectiveness of our approach on both dense 3D indoor point clouds and sparse outdoor LiDAR point clouds.

In coded aperture snapshot spectral compressive imaging (CASSI) systems, hyper-spectral image (HSI) reconstruction methods are employed to recover the spatial-spectral signal from a compressed measurement.

There are mainly two notable types of SGMs which are inherent for different learning problems.

The matrix completion problem seeks to recover a d d ground truth matrix of low rank r d from observations of its individual elements. Real-world matrix completion is often a huge-scale optimization problem, with d so large that even the simplest full-dimension vector operations with O ( d) time complexity become prohibitively expensive. Stochastic gradient descent (SGD) is one of the few algorithms capable of solving matrix completion on a huge scale, and can also naturally handle streaming data over an evolving ground truth. Unfortunately, SGD experiences a dramatic slow-down when the underlying ground truth is ill-conditioned; it requires at least O ( log(1 /)) iterations to get -close to ground truth matrix with condition number . In this paper, we propose a preconditioned version of SGD that preserves all the favorable practical qualities of SGD for huge-scale online optimization while also making it agnostic to . For a symmetric ground truth and the Root Mean Square Error (RMSE) loss, we prove that the preconditioned SGD converges to -accuracy in O (log(1 /)) iterations, with a rapid linear convergence rate as if the ground truth were perfectly conditioned with =1 . In our experiments, we observe a similar acceleration for item-item collaborative filtering on the MovieLens25M dataset via a pair-wise ranking loss, with 100 million training pairs and 10 million testing pairs.