Asia
Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization
Yizhe Zhang, Michel Galley, Jianfeng Gao, Zhe Gan, Xiujun Li, Chris Brockett, Bill Dolan
We argue that this problem is in fact twofold.
Toward a Characterization of Loss Functions for Distribution Learning
Nika Haghtalab, Cameron Musco, Bo Waggoner
Neural Information Processing Systems http://nips.cc/
Distilled Wasserstein Learning for Word Embedding and Topic Modeling
Hongteng Xu, Wenlin Wang, Wei Liu, Lawrence Carin
Theworddistributions of topics, their optimal transports to the word distributions of documents, and the embeddings of words are learned in a unified framework. When learning thetopic model, weleverage adistilled underlying distance matrix toupdate the topic distributions and smoothly calculate the corresponding optimal transports.
Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting
Shiyang Li, Xiaoyong Jin, Yao Xuan, Xiyou Zhou, Wenhu Chen, Yu-Xiang Wang, Xifeng Yan
Neural Information Processing Systems http://nips.cc/
Learning convex polytopes with margin
Lee-Ad Gottlieb, Eran Kaufman, Aryeh Kontorovich, Gabriel Nivasch
Fortheformer setting, an extensive literature has explored the statistical and computational aspects of learning Booleanfunctions[Angluin,1992,HellersteinandServedio,2007].
Transformer-based WorkingMemoryforMultiagent ReinforcementLearningwithActionParsing
Learning in real-world multiagent tasks is challenging due to the usual partial observability ofeach agent. Previous efforts alleviate thepartial observability by historical hidden states with Recurrent Neural Networks, however, they do not consider themultiagent characters thateither themultiagent observationconsists ofanumber ofobject entities orthe action space shows clear entity interactions.