Due to the inherent model uncertainty, learning to infer Bayesian posterior from a few-shot dataset is an important step towards robust meta-learning. In this paper, we propose a novel Bayesian model-agnostic meta-learning method. The proposed method combines efficient gradient-based meta-learning with nonparametric variational inference in a principled probabilistic framework. Unlike previous methods, during fast adaptation, the method is capable of learning complex uncertainty structure beyond a simple Gaussian approximation, and during meta-update, a novel Bayesian mechanism prevents meta-level overfitting. Remaining a gradientbased method, it is also the first Bayesian model-agnostic meta-learning method applicable to various tasks including reinforcement learning. Experiment results show the accuracy and robustness of the proposed method in sinusoidal regression, image classification, active learning, and reinforcement learning.
Recent research has found that many families of machine learning models are vulnerable to adversarial examples: inputs that are specifically designed to cause the target model to produce erroneous outputs. In this survey, we focus on machine learning models in the visual domain, where methods for generating and detecting such examples have been most extensively studied. We explore a variety of adversarial attack methods that apply to image-space content, real world adversarial attacks, adversarial defenses, and the transferability property of adversarial examples. We also discuss strengths and weaknesses of various methods of adversarial attack and defense. Our aim is to provide an extensive coverage of the field, furnishing the reader with an intuitive understanding of the mechanics of adversarial attack and defense mechanisms and enlarging the community of researchers studying this fundamental set of problems.
This paper presents the findings of a study to assess the effectiveness and sustainability of a GAVI (Global Alliance of Vaccines and Immunization) sponsored, time-limited Injection Safety (INS) support. The support came in two forms: 1) in-kind, in the form of AD syringes and safety boxes, and 2) in cash, for those countries that already had a secure, multi-year source of AD syringes and safety boxes, but proposed to use INS support to strengthen their injection safety activities. In total, GAVI gave INS support for a three-year period to 58 countries: 46 with commodities and 12 with cash support. To identify variables that might be associated with financial sustainability, frequencies and cross-tabulations were run against various programmatic and socio-economic variables in the 58 countries. All but two of the 46 commodity-recipient countries were able to replace and sustain the use of AD syringes and safety boxes after the end of their GAVI INS support despite the fact that standard disposable syringes are less costly than ADs (10–15 percent differential). In addition, all 12 cash-recipient countries continued to use AD syringes and safety boxes in their immunization programs in the years following GAVI INS assistance. At the same time, countries were often not prepared for the increased waste management requirements associated with the use of the syringes, suggesting the importance of anticipating challenges with the introduction of new technologies. The sustained use of AD syringes in countries receiving injection safety support from GAVI, in a majority of cases through government financing, following the completion of three years of time-limited support, represents an early indication of how GHPs can contribute to improved health outcomes in immunization safety in the world's poorest countries in a sustainable way.
While progress has been made in crafting visually imperceptible adversarial examples, constructing semantically meaningful ones remains a challenge. In this paper, we propose a framework to generate semantics preserving adversarial examples. First, we present a manifold learning method to capture the semantics of the inputs. The motivating principle is to learn the low-dimensional geometric summaries of the inputs via statistical inference. Then, we perturb the elements of the learned manifold using the Gram-Schmidt process to induce the perturbed elements to remain in the manifold. To produce adversarial examples, we propose an efficient algorithm whereby we leverage the semantics of the inputs as a source of knowledge upon which we impose adversarial constraints. We apply our approach on toy data, images and text, and show its effectiveness in producing semantics preserving adversarial examples which evade existing defenses against adversarial attacks.
Out-of-distribution (OOD) detection is a critical task for reliable machine learning. Recent advances in representation learning give rise to developments in distance-based OOD detection, where testing samples are detected as OOD if they are relatively far away from the centroids or prototypes of in-distribution (ID) classes. However, prior methods directly take off-theshelf loss functions that suffice for classifying ID samples, but are not optimally designed for OOD detection. In this paper, we propose CIDER, a simple and effective representation learning framework by exploiting hyperspherical embeddings for OOD detection. CIDER jointly optimizes two losses to promote strong ID-OOD separability: (1) a dispersion loss that promotes large angular distances among different class prototypes, and (2) a compactness loss that encourages samples to be close to their class prototypes. We show that CIDER is effective under various settings and establishes state-of-the-art performance. On a hard OOD detection task CIFAR-100 vs. CIFAR-10, our method substantially improves the AUROC by 14.20% compared to the embeddings learned by the cross-entropy loss.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.