We have composed an overview of activation functions in artificial neural networks here.
Category Archives: New Paper
Optimization landscapes in deep learning
We analyze the optimization landscapes of feedforward neural networks here. We show especially that the landscapes of wide networks do not have spurious local minima.
Statistics and artificial intelligence
We have discussed the role of statistics in artificial intelligence here.
Robust deep learning
We have established risk bounds for robust deep learning here.
Layer sparsity in neural networks
We have put a new paper about layer sparsity in neural networks on arXiv.
Inference in Labor Economics
We have now put our paper “A pipeline for variable selection and false discovery rate control with an application in labor economics” on arXiv. The paper will be part of the Annual Congress of the Swiss Society of Economics and Statistics in 2021. Congratulations Sophie-Charlotte!
Statistical Guarantees for Deep Learning
We have derived statistical guarantees for deep learning here. Well done, Mahsa and Fang! ⚡⚡⚡
Calibrating the Graphical Lasso
We have established a new strategy for calibrating the graphical lasso here. Great work, Mike! 🍷
Lasso in Theory and Practice
We have uploaded a new paper on the lasso’s effective noise and on consequences for calibration and inference here. Thanks to Michael for the great collaboration!
Ridge Regression Without Tuning Parameters
We have uploaded a paper on tuning-free ridge regression here. Well done, Shih-Ting and Fang!