Average Top-k Loss google
In this work, we introduce the average top-$k$ (AT$_k$) loss as a new ensemble loss for supervised learning, which is the average over the $k$ largest individual losses over a training dataset. We show that the AT$_k$ loss is a natural generalization of the two widely used ensemble losses, namely the average loss and the maximum loss, but can combines their advantages and mitigate their drawbacks to better adapt to different data distributions. Furthermore, it remains a convex function over all individual losses, which can lead to convex optimization problems that can be solved effectively with conventional gradient-based method. We provide an intuitive interpretation of the AT$_k$ loss based on its equivalent effect on the continuous individual loss functions, suggesting that it can reduce the penalty on correctly classified data. We further give a learning theory analysis of MAT$_k$ learning on the classification calibration of the AT$_k$ loss and the error bounds of AT$_k$-SVM. We demonstrate the applicability of minimum average top-$k$ learning for binary classification and regression using synthetic and real datasets. …

Price of Fairness (PoF) google
We introduce a flexible family of fairness regularizers for (linear and logistic) regression problems. These regularizers all enjoy convexity, permitting fast optimization, and they span the rang from notions of group fairness to strong individual fairness. By varying the weight on the fairness regularizer, we can compute the efficient frontier of the accuracy-fairness trade-off on any given dataset, and we measure the severity of this trade-off via a numerical quantity we call the Price of Fairness (PoF). The centerpiece of our results is an extensive comparative study of the PoF across six different datasets in which fairness is a primary consideration. …

Recurrent Additive Networks (RAN) google
We introduce recurrent additive networks (RANs), a new gated RNN which is distinguished by the use of purely additive latent state updates. At every time step, the new state is computed as a gated component-wise sum of the input and the previous state, without any of the non-linearities commonly used in RNN transition dynamics. We formally show that RAN states are weighted sums of the input vectors, and that the gates only contribute to computing the weights of these sums. Despite this relatively simple functional form, experiments demonstrate that RANs outperform both LSTMs and GRUs on benchmark language modeling problems. This result shows that many of the non-linear computations in LSTMs and related networks are not essential, at least for the problems we consider, and suggests that the gates are doing more of the computational work than previously understood. …

Advertisements