Unified Sample-Optimal Property Estimation in Near-Linear Time
Let k be the collection of distributions over the alphabet[k]:= {1,2,...,k}, and [k] be the set of finite sequences over[k].
A convex program for bilinear inversion of sparse vectors
Alireza Aghasi, Ali Ahmed, Paul Hand, Babhru Joshi
Neural Information Processing Systems http://nips.cc/
- North America > Canada > Quebec > Montreal (0.04)
- Asia > Pakistan > Punjab > Lahore Division > Lahore (0.04)
eec7fee9a8595ca964b9a11562767345-Supplemental-Conference.pdf
A.1 ModelArchitecture The architecture of the SinGAN used in our paper follows that in [4]. The trade-off parameter in WGAN-GP [3] is set to0.1 for gradient penalty. Adam[5]isadoptedasthe stochastic optimizer with aninitial learning rate of0.0005and adecay factor of0.1after finishing 80% of iterations, and we set the maximum number of training iterations to2,000. C.2 Per-StageWeightDistribution In addition to total weight distribution, the comparison of per-stage weight distribution is also provided.
- Europe > Norway > Eastern Norway > Oslo (0.04)
- Asia > Singapore (0.04)
- South America > Peru > Lima Department > Lima Province > Lima (0.04)
- (5 more...)
- Research Report > Experimental Study (1.00)
- Research Report > New Finding (0.68)
- Health & Medicine > Therapeutic Area > Oncology (1.00)
- Health & Medicine > Diagnostic Medicine (1.00)
- Information Technology (0.93)
Maximum Entropy Monte-Carlo Planning
Chenjun Xiao, Ruitong Huang, Jincheng Mei, Dale Schuurmans, Martin Müller
The idea is to augment Monte-Carlo TreeSearch (MCTS) withmaximum entropypolicyoptimization, evaluatingeach search node bysoftmax values back-propagated from simulation.
Fooling Neural Network Interpretations via Adversarial Model Manipulation
Juyeon Heo, Sunghwan Joo, Taesup Moon
Neural Information Processing Systems http://nips.cc/
- South America > Paraguay > Asunción > Asunción (0.04)
- North America > Canada (0.04)
- Asia > South Korea > Gyeonggi-do > Suwon (0.04)