Overview
Contents of Appendix A Extended Literature Review 14 B Time Uniform Lasso Analysis 15 C Results on Exploration 18 C.1 ALE
Table 2 compares recent work on sparse linear bandits based on a number of important factors. Some of the mentioned bounds depend on problem-dependent parameters (e.g. Carpentier and Munos [ 2012 ] assume that the action set is a Euclidean ball, and that the noise is directly added to the parameter vector, i.e. In this setting, Carpentier and Munos [ 2012 ] present a O ( d p n) regret bound. Li et al. [ 2022 ] require a stronger condition This is generally not true, but may hold with high probability.
Anytime Model Selection in Linear Bandits
M different samples in parallel from the environment so that the reward for each agent is realized.
Beyond Deep Ensembles: A Large-Scale Evaluation of Bayesian Deep Learning under Distribution Shift
We compare the algorithms on a wide range of large, convolutional and transformer-based neural network architectures.
Battle of the Backbones
Diffusion backbone, across a diverse set of computer vision tasks ranging from classification to object detection to OOD generalization and more.
Bayesian Semi-supervised Learning with Graph Gaussian Processes
Yin Cheng Ng, Nicolò Colombo, Ricardo Silva
Neural Information Processing Systems http://nips.cc/
Graphcode: Learning from multiparameter persistent homology using graph neural networks
Graphcodes handle datasets that are filtered along two real-valued scale parameters.
