Statistical Learning
No RL, No Simulation: Learning to Navigate without Navigating
Our approach, No RL, No Simulator (NRNS), is simple and scalable, yet highly effective. NRNS outperforms RL-based formulations by a significant margin.
A Appendix
A.2.5 Loss Function and Optimizer For all the experiments except N-MNIST in this work, we use cross entropy and stochastic gradient
Exploring the Algorithm-Dependent Generalization of AUPRC Optimization with List Stability Peisong Wen
Stochastic optimization of the Area Under the Precision-Recall Curve (AUPRC) is a crucial problem for machine learning. Although various algorithms have been extensively studied for AUPRC optimization, the generalization is only guaranteed in the multi-query case. In this work, we present the first trial in the single-query generalization of stochastic AUPRC optimization. For sharper generalization bounds, we focus on algorithm-dependent generalization. There are both algorithmic and theoretical obstacles to our destination.
Fast Abductive Learning by Similarity-based Consistency Optimization Y u-Xuan Huang
However, to enable effective abduction, previous approaches need an initialized perception model that discriminates the input raw instances.
DeepMed: Semiparametric Causal Mediation Analysis with Debiased Deep Learning
Causal inference is no exception.
