The aim of multi-output learning is to simultaneously predict multiple outputs given an input.
It is an important learning problem for decision-making since making decisions in the real …

Cross-entropy is a widely used loss function in applications. It coincides with the logistic loss
applied to the outputs of a neural network, when the softmax is used. But, what guarantees …

Classifiers used in the wild, in particular for safety-critical systems, should not only have
good generalization properties but also should know when they don't know, in particular …

This paper presents a margin-based multiclass generalization bound for neural networks
that scales with their margin-normalized" spectral complexity": their Lipschitz constant …

Many real-world analytics problems involve two significant challenges: prediction and
optimization. Because of the typically complex nature of each challenge, the standard …

In many applications of classifier learning, training data suffers from label noise. Deep
networks are learned using huge training data where the problem of noisy labels is …

Generating adversarial examples is a critical step for evaluating and improving the
robustness of learning machines. So far, most existing methods only work for classification …

Abstract Distributionally Robust Supervised Learning (DRSL) is necessary for building
reliable machine learning systems. When machine learning is deployed in the real world, its …

Ranking has been extensively studied in information retrieval, machine learning and
statistics. A central problem in ranking is to design a ranking measure for evaluation of …

A large-scale deep model pre-trained on massive labeled or unlabeled data transfers well to
downstream tasks. Linear evaluation freezes parameters in the pre-trained model and trains …