Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Li, Yixuan"'
Out-of-distribution (OOD) learning often relies heavily on statistical approaches or predefined assumptions about OOD data distributions, hindering their efficacy in addressing multifaceted challenges of OOD generalization and OOD detection in real-w
Externí odkaz:
http://arxiv.org/abs/2408.07772
Autor:
Burapacheep, Jirayu, Li, Yixuan
The ability to detect out-of-distribution (OOD) inputs is critical to guarantee the reliability of classification models deployed in an open environment. A fundamental challenge in OOD detection is that a discriminative classifier is typically traine
Externí odkaz:
http://arxiv.org/abs/2408.04851
Supervised learning aims to train a classifier under the assumption that training and test data are from the same distribution. To ease the above assumption, researchers have studied a more realistic setting: out-of-distribution (OOD) detection, wher
Externí odkaz:
http://arxiv.org/abs/2404.04865
Using unlabeled data to regularize the machine learning models has demonstrated promise for improving safety and reliability in detecting out-of-distribution (OOD) data. Harnessing the power of unlabeled in-the-wild data is non-trivial due to the het
Externí odkaz:
http://arxiv.org/abs/2402.03502
Supervised learning aims to train a classifier under the assumption that training and test data are from the same distribution. To ease the above assumption, researchers have studied a more realistic setting: out-of-distribution (OOD) detection, wher
Externí odkaz:
http://arxiv.org/abs/2210.14707
Classifiers in machine learning are often brittle when deployed. Particularly concerning are models with inconsistent performance on specific subgroups of a class, e.g., exhibiting disparities in skin cancer classification in the presence or absence
Externí odkaz:
http://arxiv.org/abs/2008.06775
We present a multi-agent actor-critic method that aims to implicitly address the credit assignment problem under fully cooperative settings. Our key motivation is that credit assignment among agents may not require an explicit formulation as long as
Externí odkaz:
http://arxiv.org/abs/2007.02529
Detecting out-of-distribution (OOD) inputs is critical for safely deploying deep learning models in an open-world setting. However, existing OOD detection solutions can be brittle in the open world, facing various types of adversarial OOD inputs. Whi
Externí odkaz:
http://arxiv.org/abs/2006.15207
Detecting out-of-distribution (OOD) inputs is critical for safely deploying deep learning models in the real world. Existing approaches for detecting OOD examples work well when evaluated on benign in-distribution and OOD samples. However, in this pa
Externí odkaz:
http://arxiv.org/abs/2003.09711
Traditional stock market prediction methods commonly only utilize the historical trading data, ignoring the fact that stock market fluctuations can be impacted by various other information sources such as stock related events. Although some recent wo
Externí odkaz:
http://arxiv.org/abs/1809.00306