Technology
Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks
Yusuke Tsuzuku, Issei Sato, Masashi Sugiyama
Adversarial training [10, 16, 18], which injects adversarially perturbed dataintotraining data,isapromising approach. Many other heuristics have been developed to make neural networks insensitive against small perturbations on inputs.
Unsupervised Keypoint Learning for Guiding Class-Conditional Video Prediction
Yunji Kim, Seonghyeon Nam, In Cho, Seon Joo Kim
Neural Information Processing Systems http://nips.cc/
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/
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.
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.