Europe
Taming Heavy-Tailed Losses in Adversarial Bandits and the Best-of-Both-Worlds Setting
Consider the multi-armed bandits (MAB) problem (Auer et al., 2002a,b), which is a useful framework Typically, the losses are assumed to have a support on a bounded interval (e.g., Moreover, while the former ones enjoy a logarithmic regret (i.e., These performance discrepancies motivated the study of the Best-of-Both-W orlds (BOBW) setting.
Deep Neural Networks with Box Convolutions
Due to its ability to integrate information over large boxes, the new layer facilitates long-range propagation of information and leads to the efficient increase ofthe receptivefields ofnetwork units.
Average Case Column Subset Selection for Entrywise $\ell_1$-Norm Loss
Zhao Song, David Woodruff, Peilin Zhong
Nevertheless, we show that under certain minimal and realistic distributional settings, it is possible to obtain a (1+ null)-approximation with a nearly linear running time and poly (k/null) + O ( k log n) columns. Namely, we show that if the input matrix A has the form A = B + E, where B is an arbitrary rank-k matrix, and E is a matrix with i.i.d.
Flow-based Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection - Appendix Haibao Y u 1, 2, Yingjuan T ang
Mean A verage Precision (mAP). For VIC3D object detection, we focus on the obstacles around the ego vehicle. There are two metrics used for evaluation: BEV@mAP and 3D@mAP . BEV@mAP evaluates the 3D boxes in the bird's-eye view and ignores the In our implementation, we ignore the transmission cost of calibration files and timestamps. For early fusion, we calculate the transmission cost of transmitting raw data.
Flow-Based Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection Haibao Yu1, 2, Yingjuan T ang
Cooperatively utilizing both ego-vehicle and infrastructure sensor data can significantly enhance autonomous driving perception abilities. However, the uncertain temporal asynchrony and limited communication conditions can lead to fusion misalignment and constrain the exploitation of infrastructure data.
Learning to Predict Layout-to-image Conditional Convolutions for Semantic Image Synthesis
Xihui Liu, Guojun Yin, Jing Shao, Xiaogang Wang, hongsheng Li
On the other hand, we rethink the functionality of convolutional layers for image synthesis.
Certified Robustness via Dynamic Margin Maximization and Improved Lipschitz Regularization
To improve the robustness of deep classifiers against adversarial perturbations, many approaches have been proposed, such as designing new architectures with better robustness properties (e.g., Lipschitz-capped networks), or modifying the
Chaining Mutual Information and Tightening Generalization Bounds
Amir Asadi, Emmanuel Abbe, Sergio Verdu
Neural Information Processing Systems http://nips.cc/
Multi-view Masked Contrastive Representation Learning for Endoscopic Video Analysis
Specifically, we propose a multi-view masking strategy for addressing the challenges of endoscopic videos.