相关论文: Empirical Study on Optimizer Selection for Out-of-…

As training datasets grow larger, we aspire to develop models that generalize well to any diverse test distribution, even if the latter deviates significantly from the training data. Various approaches like domain adaptation, domain…

Out-of-distribution (OOD) detection has recently gained substantial attention due to the importance of identifying out-of-domain samples in reliability and safety. Although OOD detection methods have advanced by a great deal, they are still…

The capability of reliably detecting out-of-distribution samples is one of the key factors in deploying a good classifier, as the test distribution always does not match with the training distribution in most real-world applications. In…

We study the problem of out-of-distribution dynamics (OODD) detection, which involves detecting when the dynamics of a temporal process change compared to the training-distribution dynamics. This is relevant to applications in control,…

Deep learning algorithms - typically consisting of a class of deep neural networks trained by a stochastic gradient descent (SGD) optimization method - are nowadays the key ingredients in many artificial intelligence (AI) systems and have…

Deep learning on graphs has shown remarkable success across numerous applications, including social networks, bio-physics, traffic networks, and recommendation systems. Regardless of their successes, current methods frequently depend on the…

Deep learning optimization relies heavily on the assumption of smooth loss landscapes, a condition systematically violated by modern architectures due to non-smooth components such as ReLU activations and quantization operators. In such…

Machine learning algorithms aim to find patterns from observations, which may include some noise, especially in robotics domain. To perform well even with such noise, we expect them to be able to detect outliers and discard them when…

The ADAM optimizer is exceedingly popular in the deep learning community. Often it works very well, sometimes it doesn't. Why? We interpret ADAM as a combination of two aspects: for each weight, the update direction is determined by the…

Out-of-distribution (O.O.D.) generalization remains to be a key challenge for real-world machine learning systems. We describe a method for O.O.D. generalization that, through training, encourages models to only preserve features in the…

In this paper, we study the differences and commonalities between statistically out-of-distribution (OOD) samples and adversarial (Adv) samples, both of which hurting a text classification model's performance. We conduct analyses to compare…

In this work, to efficiently help escape the stationary and saddle points, we propose, analyze, and generalize a stochastic strategy performed as an operator for a first-order gradient descent algorithm in order to increase the target…

Deep neural networks often suffer from overconfidence which can be partly remedied by improved out-of-distribution detection. For this purpose, we propose a novel approach that allows for the generation of out-of-distribution datasets based…

Deep neural networks for image classification only learn to map in-distribution inputs to their corresponding ground truth labels in training without differentiating out-of-distribution samples from in-distribution ones. This results from…

Adaptive gradient methods have achieved remarkable success in training deep neural networks on a wide variety of tasks. However, not much is known about the mathematical and statistical properties of this family of methods. This work aims…

Consider a prediction setting with few in-distribution labeled examples and many unlabeled examples both in- and out-of-distribution (OOD). The goal is to learn a model which performs well both in-distribution and OOD. In these settings,…

Deep learning methods - consisting of a class of deep neural networks (DNNs) trained by a stochastic gradient descent (SGD) optimization method - are nowadays key tools to solve data driven supervised learning problems. Despite the great…

Adaptive optimization methods, which perform local optimization with a metric constructed from the history of iterates, are becoming increasingly popular for training deep neural networks. Examples include AdaGrad, RMSProp, and Adam. We…

Out-of-distribution (OOD) learning deals with scenarios in which training and test data follow different distributions. Although general OOD problems have been intensively studied in machine learning, graph OOD is only an emerging area of…

This paper introduces a universal approach to seamlessly combine out-of-distribution (OOD) detection scores. These scores encompass a wide range of techniques that leverage the self-confidence of deep learning models and the anomalous…