arXiv research

Validates neural networks inputs to protect against adversarial examples.

MINs learn inverse mappings for high-dimensional optimization problems.

We analyze the adversarial examples problem in terms of a model's fault tolerance with respect to its input. Whereas previous work focuses on arbitrarily strict threat models, i.e., $ε$-perturbations, we consider arbitrary valid inputs and propose an information-based characteristic for evaluating tolerance to diverse …

VAIOM models financial returns using continuous input and categorical output.

The paper proposes a method to detect and filter noisy or mislabeled data using pointwise mutual information.

Study tests if input gradients highlight discriminative features, finds they often fail.

One basic requirement of many studies is the necessity of classifying data. Clustering is a proposed method for summarizing networks. Clustering methods can be divided into two categories named model-based approaches and algorithmic approaches. Since the most of clustering methods depend on their input parameters, it i…

Method extracts knowledge from LSTM for sequence validation.

An intriguing property of deep neural networks is their inherent vulnerability to adversarial inputs, which significantly hinders their application in security-critical domains. Most existing detection methods attempt to use carefully engineered patterns to distinguish adversarial inputs from their genuine counterparts…

LLMs fail to match statistical ground truth despite stable run-to-run performance.

We propose a novel approach for loss reserving based on deep neural networks. The approach allows for joint modeling of paid losses and claims outstanding, and incorporation of heterogeneous inputs. We validate the models on loss reserving data across lines of business, and show that they improve on the predictive accu…

Normalizing Flows improve prediction interval efficiency in CP.

A new method builds sparse polynomial chaos expansions for models with dependent inputs.

FuncNN package enables deep learning with functional covariates.

A new method warps inputs to learn nonstationary kernels efficiently.

Deep neural networks (DNNs) are notorious for their vulnerability to adversarial attacks, which are small perturbations added to their input images to mislead their prediction. Detection of adversarial examples is, therefore, a fundamental requirement for robust classification frameworks. In this work, we present a met…

This paper develops a framework for training and evaluating neural networks for MPC.

Reliability is a critical consideration to DL-based systems. But the statistical nature of DL makes it quite vulnerable to invalid inputs, i.e., those cases that are not considered in the training phase of a DL model. This paper proposes to perform data sanity check to identify invalid inputs, so as to enhance the reli…

This study revisits UQ validation methods based on consistency and adaptivity concepts.

While variational dropout approaches have been shown to be effective for network sparsification, they are still suboptimal in the sense that they set the dropout rate for each neuron without consideration of the input data. With such input-independent dropout, each neuron is evolved to be generic across inputs, which m…

Techniques for understanding the functioning of complex machine learning models are becoming increasingly popular, not only to improve the validation process, but also to extract new insights about the data via exploratory analysis. Though a large class of such tools currently exists, most assume that predictions are p…

Theory proposes neural networks can be initialized for optimal information transmission.

Improved code translation by preserving structure with composed fine-tuning.

We present an approach for reconfiguration of dynamic visual sensor networks with deep reinforcement learning (RL). Our RL agent uses a modified asynchronous advantage actor-critic framework and the recently proposed Relational Network module at the foundation of its network architecture. To address the issue of sample…

For many years, a combination of principal component analysis (PCA) and independent component analysis (ICA) has been used for blind source separation (BSS). However, it remains unclear why these linear methods work well with real-world data that involve nonlinear source mixtures. This work theoretically validates that…

Deep Neural Networks(DNN) have excessively advanced the field of computer vision by achieving state of the art performance in various vision tasks. These results are not limited to the field of vision but can also be seen in speech recognition and machine translation tasks. Recently, DNNs are found to poorly fail when …

This paper introduces NPR, a technique to improve Bayesian inference for multi-modal, high-dimensional simulations.

WE constructs GP kernels for mixed inputs using weighted EDMs.

SOCP uses SOM to find groups and local calibration buffers for better regional coverage.

CLUE method interprets uncertainty from BNNs by showing how inputs change to increase confidence.

ManifoldShap improves model explanations by restricting evaluations to the data manifold.

CoLT assesses neural posterior estimates by detecting discrepancies across conditioning inputs.

Constraint-based learning reduces the burden of collecting labels by having users specify general properties of structured outputs, such as constraints imposed by physical laws. We propose a novel framework for simultaneously learning these constraints and using them for supervision, bypassing the difficulty of using d…

Multi-SpaCE generates valid counterfactual explanations for multivariate time series data.

The paper evaluates different graph input representations for urban network analysis.

Random deep neural networks are robust to adversarial examples, scaling with input size and dimension.

Proposes a framework to incorporate global sensitivity into local surrogate models.

Adversarial validation detects concept drift in user targeting systems.

Monotonic improvement in uncertainty estimation with Gaussian processes as dimension increases.

New approach ties loss curvature to model performance in deep learning.

Reservoir Computing (RC) provides an efficient way for designing dynamical recurrent neural models. While training is restricted to a simple output component, the recurrent connections are left untrained after initialization, subject to stability constraints specified by the Echo State Property (ESP). Literature condit…

It has recently been shown that neural networks but also other classifiers are vulnerable to so called adversarial attacks e.g. in object recognition an almost non-perceivable change of the image changes the decision of the classifier. Relatively fast heuristics have been proposed to produce these adversarial inputs bu…

New neural network approximates convex option prices.

Conformal prediction is a technique for constructing prediction intervals that attain valid coverage in finite samples, without making distributional assumptions. Despite this appeal, existing conformal methods can be unnecessarily conservative because they form intervals of constant or weakly varying length across the…

Fairness is a critical trait in decision making. As machine-learning models are increasingly being used in sensitive application domains (e.g. education and employment) for decision making, it is crucial that the decisions computed by such models are free of unintended bias. But how can we automatically validate the fa…

We consider the problem of joint modelling of metabolic signals and gene expression in systems biology applications. We propose an approach based on input-output factorial hidden Markov models and propose a structured variational inference approach to infer the structure and states of the model. We start from the class…

New approach links machine learning reliability to epistemic uncertainty.

Proposes a method for explaining ranking decisions in learning systems.