Technology
Flexible neural representation for physics prediction
Damian Mrowca, Chengxu Zhuang, Elias Wang, Nick Haber, Li F. Fei-Fei, Josh Tenenbaum, Daniel L. Yamins
Neural Information Processing Systems http://nips.cc/
Thermostat-assisted continuously-tempered Hamiltonian Monte Carlo for Bayesian learning
Rui Luo, Jianhong Wang, Yaodong Yang, Jun WANG, Zhanxing Zhu
Neural Information Processing Systems http://nips.cc/
Multivariate Distributionally Robust Convex Regression under Absolute Error Loss
Jose Blanchet, Peter W. Glynn, Jun Yan, Zhengqing Zhou
We minimize over convex functions the maximum (over Wasserstein perturbations of the empirical measure) of the absolute regression errors.
Multi-Agent First Order Constrained Optimization in Policy Space
In the realm of multi-agent reinforcement learning (MARL), achieving high performance is crucial for a successful multi-agent system.
NeuralFuse: Learning to Recover the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes Hao-Lun Sun
Energy-efficient computing is of primary importance to the effective deployment of deep neural networks (DNNs), particularly in edge devices and in on-chip AI systems. Increasing DNN computation's energy efficiency and lowering its carbon footprint require iterative efforts from both chip designers and algorithm developers.
Non-Local Recurrent Network for Image Restoration
Ding Liu, Bihan Wen, Yuchen Fan, Chen Change Loy, Thomas S. Huang
Many classic methods have shown non-local self-similarity in natural images to be an effective prior for image restoration. However, it remains unclear and challenging to make use of this intrinsic property via deep networks.
Efficient Approximation of Deep ReLU Networks for Functions on Low Dimensional Manifolds
Minshuo Chen, Haoming Jiang, Wenjing Liao, Tuo Zhao
Empirical results, however,suggest thatnetworks of moderate size already yield appealing performance. To explain such a gap, a common belief is that many data sets exhibit low dimensional structures, and can be modeled as samples near a low dimensional manifold.
Neural Multi-Objective Combinatorial Optimization with Diversity Enhancement (Appendix) A Reference point and hypervolume ratio
In the inference process, the submodel is used to solve the corresponding subproblem. The input dimensions of the node features vary with different problems. A masking mechanism is adopted in each decoding step to ensure the solution feasibility. For MOTSP, the visited nodes are masked. NHDE-M usually spends relatively more inference time than MDRL with the same number of weights.