Recent researches reveal that deep neural networks are sensitive to label noises hence leading poor generalization performance in some tasks. Although different robust loss functions have been proposed remedy this issue, they suffer from an underfitting problem, thus not sufficient learn accurate models. On the other hand, commonly used Cross Entropy (CE) loss, which shows high standard supervi...

Recovering a dense depth image from sparse LiDAR scans is challenging task. Despite the popularity of color-guided methods for sparse-to-dense completion, they treated pixels equally during optimization, ignoring uneven distribution characteristics in map and accumulated outliers synthesized ground truth. In this work, we introduce uncertainty-driven loss functions to improve robustness complet...

This paper presents an extension of stochastic gradient descent for the minimization Lipschitz continuous loss functions. Our motivation is use in non-smooth non-convex optimization problems, which are frequently encountered applications such as machine learning. Using Clarke $$\epsilon $$ -subdifferential, we prove non-asymptotic convergence to approximate stationary point expectation proposed...

When a forecast ft,h of a variable Yt+h is made at time t for h periods ahead, the loss (or cost) will arise if a forecast turns to be different from the actual value. The loss function of the forecast error et+h = Yt+h − ft,h, is denoted as c(Yt+h, ft,h). The loss function can depend on the time of prediction and so it can be ct+h(Yt+h, ft,h). If the loss function is not changing with time and...

In this paper, we provide a general theorem that establishes a correspondence between surrogate loss functions in classification and the family of f -divergences. Moreover, we provide constructive procedures for determining the f -divergence induced by a given surrogate loss, and conversely for finding all surrogate loss functions that realize a given f -divergence. Next we introduce the notion...