Statistical Learning
Smoothed Analysis of Discrete Tensor Decomposition and Assemblies of Neurons
Nima Anari, Constantinos Daskalakis, Wolfgang Maass, Christos Papadimitriou, Amin Saberi, Santosh Vempala
Neural Information Processing Systems http://nips.cc/
Distributed Stochastic Optimization via Adaptive SGD
Ashok Cutkosky, Rรณbert Busa-Fekete
Neural Information Processing Systems http://nips.cc/
TheEffectsofRegularizationandDataAugmentation areClassDependent
Machine learning and deep learning aim at learning systems to solve as accurately as possible a given task at hand [LeCun et al., 1998, Bishop and Nasrabadi, 2006, Jordan and Mitchell, 2015].
Uncertainty Sampling is Preconditioned Stochastic Gradient Descent on Zero-One Loss
Stephen Mussmann, Percy S. Liang
Neural Information Processing Systems http://nips.cc/
SySCD: A System-Aware Parallel Coordinate Descent Algorithm
Nikolas Ioannou, Celestine Mendler-Dรผnner, Thomas Parnell
Neural Information Processing Systems http://nips.cc/
Parameter-free Clipped Gradient Descent Meets Polyak Y uki T akezawa
Gradient descent and its variants are de facto standard algorithms for training machine learning models. As gradient descent is sensitive to its hyperparame-ters, we need to tune the hyperparameters carefully using a grid search.
Self-Supervised Pretraining for Large-Scale Point Clouds
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.
Federated Learning with Bilateral Curation for Partially Class-Disjoint Data Ziqing Fan
However, they cause another problem: space waste for personal tasks.
