馒头and花卷

摘要： motivation 提高网络的一个有用的技巧就是增加训练数据: 真实数据, 或者用GAN拟合的数据. 这里想要研究的是, 噪声是否能够算作这类数据. 以CIFAR-10为例, 令 \[ f: x \in \mathcal{X} \rightarrow p \in \mathbb{R}^{11}, 阅读全文

摘要： Choi H. I. Lecture 4: Exponential family of distributions and generalized linear model (GLM). 定义 定义: 一个分布具有如下形式的密度函数: \[ f_{\theta}(x) = \frac{1}{Z(\t 阅读全文

摘要： Sufficient statistic - Wikipedia Sufficient statistic - arizona 定义 统计量是一些随机样本$X_1, X_2, \cdots, X_n$的函数 \[ T = r(X_1, X_2, \cdots, X_n). \] 样本$X$的分布$f 阅读全文

摘要： Yu Y., Chen J., Gao T. and Yu M. DAG-GNN: DAG structure learning with graph neural networks. In International Conference on Machine Learning (ICML), 2 阅读全文

摘要： Ng I., Fang Z., Zhu S., Chen Z. and Wang J. Masked Gradient-Based Causal Structure Learning. arXiv preprint arXiv:1911.10500, 2019. 概 非线性, 自动地学习因果图. 主 阅读全文

摘要： motivation BBN 对于处理长尾问题非常有效, 我在想, 能不能类似地用在鲁棒问题上. 思想很简单, 就是上面用干净数据, 下面用对抗样本(其用$\alpha=0.5$的eval mode 生成), 但是结果非常差. settings - batch_size: 128 - beta1: 阅读全文

摘要： DAGs with NO TEARS: Continuous Optimization for Structure Learning Zheng X., Aragam B., Ravikumar P. and Xing E. DAGs with NO TEARS: Continuous Optimi 阅读全文

摘要： Jang E., Gu S. and Poole B. Categorical reparameterization with gumbel-softmax. In International Conference On Learning Representations (ICLR), 2017. 阅读全文

摘要： 概 感觉这个分布的含义很有用啊, 能预测‘最大', 也就是自然灾害, 太牛了. 主要内容 定义 [Gumbel distribution-wiki](Gumbel distribution - Wikipedia) 其分布函数和概率密度函数分别为: \[ F(x; \mu, \beta) = e^{ 阅读全文

摘要： Locatello F., Bauer S., Lucic M., R"{a}tsch G., Gelly S. Sch"{o}lkopf and Bachem Olivier. Challenging common assumptions in the unsupervised learning 阅读全文

摘要： 源 Exponential moving average (EMA) 是一个非常有用的trick, 起到加速训练的作用. 近来发现, 该技巧还可以用于提高网络鲁棒性(约1% ~ 2%). EMA的流程很简单, $f(\cdot;\theta)$是我们用于训练的网络, 则在每次迭代结束后进行: \[ 阅读全文

摘要： Ioffe S. and Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift. In International Conference on M 阅读全文

摘要： Rosenbaum P. and Rubin D. The Central Role of the Propensity Score in Observational Studies For Causal Effects. Biometrika, 1983, 70(1): 41-55. Propen 阅读全文

摘要： Sehwag V., Mahloujifar S., Handina T., Dai S., Xiang C., Chiang M. and Mittal P. Improving adversarial robustness using proxy Distributions. arXiv pre 阅读全文

摘要： > Prabhushankar M., Kwon G., Temel D. and AlRegib G. Contrastive explanation in neural networks. In 2020 IEEE International Conference on Image Proces 阅读全文

摘要： Gowal S., Dvijotham K., Stanforth R., Bunel R., Qin C., Uesato J., Arandjelovic R., Mann T. & Kohli P. Scalable verified training for provably robust 阅读全文

摘要： Zhang H., Zhang Z., Odena A. and Lee H. CONSISTENCY REGULARIZATION FOR GENERATIVE ADVERSARIAL NETWORKS. ICLR, 2020. Zhao Z., Singh S., Lee H., Zhang Z 阅读全文

摘要： Zhao S., Liu Z., Lin J., Zhu J. and Han S. Differentiable Augmentation for Data-Efficient GAN Training. NIPS, 2020. Karras T., Aittala M., Hellsten J. 阅读全文

摘要： Zhou B., Khosla A., Lapedriza A., Oliva A. and Torralba A. Learning Deep Features for Discriminative Localization. CVPR, 2016. Selvaraju R., Das A., V 阅读全文

摘要： Niu Y., Tang K., Zhang H., Lu Z., Hua X. and Wen J. Counterfactual VQA: A Cause-Effect Look at Language Bias. CVPR, 2021. 概 利用因果分析消除VQA(Visual Questio 阅读全文