A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
XEnsemble improves DNN robustness against adversarial and out-of-distribution inputs.
Deep learning provides a powerful tool for machine perception when the observations resemble the training data. However, real-world robotic systems must react intelligently to their observations even in unexpected circumstances. This requires a system to reason about its own uncertainty given unfamiliar, out-of-distrib…
Proposes training neural networks to predict uncertainty for out-of-distribution inputs.
Recent work has shown that deep generative models assign higher likelihood to out-of-distribution inputs than to training data. We show that a factor underlying this phenomenon is a mismatch between the nature of the prior distribution and that of the data distribution, a problem found in widely used deep generative mo…
Improved VAE model enhances uncertainty estimation for out-of-distribution samples.
In-N-Out improves model robustness to out-of-distribution data.
Recent work has shown that deep generative models can assign higher likelihood to out-of-distribution data sets than to their training data (Nalisnick et al., 2019; Choi et al., 2019). We posit that this phenomenon is caused by a mismatch between the model's typical set and its areas of high probability density. In-dis…
p-DkNN uses deep representations to detect out-of-distribution data with statistical tests.
We present a new method for uncertainty estimation and out-of-distribution detection in neural networks with softmax output. We extend softmax layer with an additional constant input. The corresponding additional output is able to represent the uncertainty of the network. The proposed method requires neither additional…
New method improves robustness of OOD detection models.
DOODLER detects out-of-distribution inputs by reconstructing in-distribution data.
Deep learning models are known to be overconfident in their predictions on out of distribution inputs. This is a challenge when a model is trained on a particular input dataset, but receives out of sample data when deployed in practice. Recently, there has been work on building classifiers that are robust to out of dis…
Modern neural networks are very powerful predictive models, but they are often incapable of recognizing when their predictions may be wrong. Closely related to this is the task of out-of-distribution detection, where a network must determine whether or not an input is outside of the set on which it is expected to safel…
Likelihood-based generative models are a promising resource to detect out-of-distribution (OOD) inputs which could compromise the robustness or reliability of a machine learning system. However, likelihoods derived from such models have been shown to be problematic for detecting certain types of inputs that significant…
FOOD detects out-of-distribution samples quickly without needing OOD data.
Deep learning models are known to be overconfident in their predictions on out of distribution inputs. There have been several pieces of work to address this issue, including a number of approaches for building Bayesian neural networks, as well as closely related work on detection of out of distribution samples. Recent…
Single deep model detects out-of-distribution data with single forward pass.
Real-time detection of out-of-distribution data in CPS control systems.
Deep neural networks achieve superior performance in challenging tasks such as image classification. However, deep classifiers tend to incorrectly classify out-of-distribution (OOD) inputs, which are inputs that do not belong to the classifier training distribution. Several approaches have been proposed to detect OOD i…
Survey connects three DNN generalization fields for better inference.
Despite their successes, deep neural networks may make unreliable predictions when faced with test data drawn from a distribution different to that of the training data, constituting a major problem for AI safety. While this has recently motivated the development of methods to detect such out-of-distribution (OoD) inpu…
New method detects uncertainty in neural networks for out-of-distribution detection.
This paper examines how optimization methods affect the reliability of detecting inputs outside a model's training distribution.
Bayesian autoencoders improve OOD detection by addressing Bernoulli likelihood issues.
Modern deep artificial neural networks have achieved great success in the domain of computer vision and beyond. However, their application to many real-world tasks is undermined by certain limitations, such as overconfident uncertainty estimates on out-of-distribution data or performance deterioration under data distri…
Work proposes a new framework to improve uncertainty estimation in deep Bayesian models.
We introduce a measure to quantify ambiguity in deep learning models, improving their reliability.
Generative classifiers have been shown promising to detect illegal inputs including adversarial examples and out-of-distribution samples. Supervised Deep Infomax~(SDIM) is a scalable end-to-end framework to learn generative classifiers. In this paper, we propose a modification of SDIM termed SDIM-\emph{logit}. Instead …
A large body of recent work has investigated the phenomenon of evasion attacks using adversarial examples for deep learning systems, where the addition of norm-bounded perturbations to the test inputs leads to incorrect output classification. Previous work has investigated this phenomenon in closed-world systems where …
A new framework detects anomalous inputs to DNNs.
TIE framework detects out-of-distribution samples and estimates uncertainty without external datasets.
ACNML method improves uncertainty estimation for deep networks.
We consider the problem of detecting out-of-distribution images in neural networks. We propose ODIN, a simple and effective method that does not require any change to a pre-trained neural network. Our method is based on the observation that using temperature scaling and adding small perturbations to the input can separ…
Δ-UQ uses anchoring to estimate uncertainty in models.
Proposes a new criterion for reliable uncertainty estimation in deep neural networks.
Counterfactual data augmentations may not ensure OOD robustness if performed by a context-guessing machine.
DAB enriches deep networks with uncertainty estimates using a codebook of training inputs.
New approach models how explanations shift with distribution changes.
GIM uses neural networks with Gaussian distributions to detect out-of-distribution data.
Framework extends neural operators to handle functions outside training set.
Paper proposes contrastive training to improve OOD detection without needing explicit OOD examples.
Bayesian neural networks fail at out-of-distribution detection, revealing fundamental issues.
There is an increasingly apparent need for validating the classifications made by deep learning systems in safety-critical applications like autonomous vehicle systems. A number of recent papers have proposed methods for detecting anomalous image data that appear different from known inlier data samples, including reco…
Paper aims to ensure reliable detection of out-of-distribution data with certifiable worst-case guarantees.
ManifoldShap improves model explanations by restricting evaluations to the data manifold.
Improves regression models' performance on covariate shift.
In this work, we propose data augmentation methods for embeddings from pre-trained deep learning models that take a weighted combination of a pair of input embeddings, as inspired by Mixup, and combine such augmentation with extra label softening. These methods are shown to significantly increase classification accurac…
Ensemble approaches for uncertainty estimation have recently been applied to the tasks of misclassification detection, out-of-distribution input detection and adversarial attack detection. Prior Networks have been proposed as an approach to efficiently \emph{emulate} an ensemble of models for classification by paramete…