Asia
Multi-relationalPoincaréGraphEmbeddings
Hyperbolic embeddings haverecently gained attention in machine learning due totheir ability torepresent hierarchical data more accurately and succinctly than their Euclidean analogues.
Efficient Potential-based Exploration in Reinforcement Learning using Inverse Dynamic Bisimulation Metric
While a number of RL methods have been proposed to boost exploration by designing an intrinsic reward signal as exploration bonus.
Proximal Graphical Event Models
Debarun Bhattacharjya, Dharmashankar Subramanian, Tian Gao
Neural Information Processing Systems http://nips.cc/
GEQ: Gaussian Kernel Inspired Equilibrium Models
Moreover, GEQ can be perceived as a weight-tied neural network with infinite width and depth. GEQ also enjoys better theoretical properties and improved overall performance.
The continuous Bernoulli: fixing a pervasive error in variational autoencoders
Gabriel Loaiza-Ganem, John P. Cunningham
Neural Information Processing Systems http://nips.cc/
Diffusion-based ReinforcementLearningvia Q-weightedVariationalPolicyOptimization
UnlikeGaussian policies, the log-likelihood indiffusion policies isinaccessible; thus this entropy term is nontrivial. Moreover, to reduce the large variance of diffusion policies, we also develop an efficient behavior policy through action selection. This can further improve its sample efficiency during online interaction.
Learning Versatile Filters for Efficient Convolutional Neural Networks
Yunhe Wang, Chang Xu, Chunjing XU, Chao Xu, Dacheng Tao
Neural Information Processing Systems http://nips.cc/
A Unified Approach to Count-Based Weakly-Supervised Learning
High-quality labels are often very scarce, whereas unlabeled data with inferred weak labels occurs more naturally.