ICLR 2019 有什么值得关注的亮点？ 第1页

有意思的工作挺多，留着慢慢看。初略一扫倒是觉得这些论文的标题真是八仙过海。看来在这个论文投稿爆炸的年代，论文的标题跟颜值一样，是首先吸引人的东西，大家一起来学习学习。

问句开头式：

• Are adversarial examples inevitable?
• Transfer Value or Policy? A Value-centric Framework Towards Transferrable Continuous Reinforcement Learning
• How Important is a Neuron?
• How Powerful are Graph Neural Networks?
• Do Language Models Have Common Sense?
• Is Wasserstein all you need?

哲理警句式：

• Learning From the Experience of Others: Approximate Empirical Bayes in Neural Networks
• In Your Pace: Learning the Right Example at the Right Time
• Learning what you can do before doing anything
• Like What You Like: Knowledge Distill via Neuron Selectivity Transfer
• Don’s Settle for Average, Go for the Max: Fuzzy Sets and Max-Pooled Word Vectors

抖机灵式：

• Look Ma, No GANs! Image Transformation with ModifAE
• No Pressure! Addressing Problem of Local Minima in Manifold Learning
• Backplay: 'Man muss immer umkehren'
• Talk The Walk: Navigating Grids in New York City through Grounded Dialogue
• Fatty and Skinny: A Joint Training Method of Watermark
• A bird's eye view on coherence, and a worm's eye view on cohesion
• Beyond Winning and Losing: Modeling Human Motivations and Behaviors with Vector-valued Inverse Reinforcement Learning

一句总结式：

• ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness.

标题最吸引我的两篇：

• Understanding & Generalizing AlphaGo Zero
• A Solution to China Competitive Poker Using Deep Learning （斗地主深度学习算法）

最后，Jun-Yan大神也带我投了一篇蛮有意思的论文，就不剧透了。Josh Tenenbaum对论文评价的原话是：this is an excellent and inspiring paper. 感兴趣的同学可以猜猜，猜中有奖。

感觉这篇large scale GAN真的非常牛逼, 具体还没细看, 就放几张图你们感受一下...

不敢相信这张图是generated 出来的...

再看看interpolation的结果

个人比较喜欢的是他们真的在非常large scale上train这个model："The dataset contains 292M images labeled with 8.5K categories, which is two orders of magnitude larger than ImageNet"

architecture上是比较 "wide" 的resnet + non-local