arXiv research

Efficiently controls unknown linear systems with black-box interactions.

Deep-PrAE improves rare-event simulation for black-box systems.

This paper proposes a novel PGO framework to optimize systemic risk bailouts using neural networks.

Improves model classification accuracy in black-box settings.

Proposes a method to ensure accurate estimation of rare events in AI systems.

New attacks reduce bad queries in black-box classifiers, improving effectiveness.

LaMBO optimizes modular systems with switching costs, achieving better results than existing methods.

The paper certifies AI reliability via sampling and calibration, providing exact guarantees.

Hybrid neural network infers states from black-box systems.

Modern control theories such as systems engineering approaches try to solve nonlinear system problems by revelation of causal relationship or co-relationship among the components; most of those approaches focus on control of sophisticatedly modeled white-boxed systems. We suggest an application of actor-critic reinforc…

New symmetries improve meta-reinforcement learning's generalization.

Bringing transparency to black-box decision making systems (DMS) has been a topic of increasing research interest in recent years. Traditional active and passive approaches to make these systems transparent are often limited by scalability and/or feasibility issues. In this paper, we propose a new notion of black-box D…

Latent force models are systems whereby there is a mechanistic model describing the dynamics of the system state, with some unknown forcing term that is approximated with a Gaussian process. If such dynamics are non-linear, it can be difficult to estimate the posterior state and forcing term jointly, particularly when …

Interpretable machine learning has gained much attention recently. Briefness and comprehensiveness are necessary in order to provide a large amount of information concisely when explaining a black-box decision system. However, existing interpretable machine learning methods fail to consider briefness and comprehensiven…

System interprets complex treatment effects for personalized policies.

Interprets feature interactions in ad-click prediction models.

Survey of algorithms for testing AI-driven CPS safety.

New method optimizes sensor placement for stochastic systems efficiently.

Paper introduces Native Guide for generating time series counterfactual explanations.

The application of deep recurrent networks to audio transcription has led to impressive gains in automatic speech recognition (ASR) systems. Many have demonstrated that small adversarial perturbations can fool deep neural networks into incorrectly predicting a specified target with high confidence. Current work on fool…

Most of the work on interpretable machine learning has focused on designing either inherently interpretable models, which typically trade-off accuracy for interpretability, or post-hoc explanation systems, which lack guarantees about their explanation quality. We propose an alternative to these approaches by directly r…

HyperFair integrates fairness in recommender systems using probabilistic soft logic.

Many deployed learned models are black boxes: given input, returns output. Internal information about the model, such as the architecture, optimisation procedure, or training data, is not disclosed explicitly as it might contain proprietary information or make the system more vulnerable. This work shows that such attri…

A new method for optimizing black-box problems with constraints.

Paper introduces DNTs to clone black-box models efficiently.

Note that this paper is superceded by "Black-Box Adversarial Attacks with Limited Queries and Information." Current neural network-based image classifiers are susceptible to adversarial examples, even in the black-box setting, where the attacker is limited to query access without access to gradients. Previous methods -…

The lack of interpretability often makes black-box models difficult to be applied to many practical domains. For this reason, the current work, from the black-box model input port, proposes to incorporate data-based prior information into the black-box soft-margin SVM model to enhance its interpretability. The concept …

Algorithm optimizes and infers performance online, improving reliability.

Semi-parametric framework for nonlinear system identification

Hybrid models combine interpretable and complex models for better performance and control.

Machine Learning models are often composed of pipelines of transformations. While this design allows to efficiently execute single model components at training time, prediction serving has different requirements such as low latency, high throughput and graceful performance degradation under heavy load. Current predicti…

Machine Learning systems are vulnerable to adversarial attacks and will highly likely produce incorrect outputs under these attacks. There are white-box and black-box attacks regarding to adversary's access level to the victim learning algorithm. To defend the learning systems from these attacks, existing methods in th…

Current neural network-based classifiers are susceptible to adversarial examples even in the black-box setting, where the attacker only has query access to the model. In practice, the threat model for real-world systems is often more restrictive than the typical black-box model where the adversary can observe the full …

Tree ensemble method tackles multi-objective constrained optimization in energy systems.

New method optimizes expensive simulations for complex systems.

Improves relevancy of black-box anomaly detectors with user feedback.

Parameter inference for stochastic differential equations is challenging due to the presence of a latent diffusion process. Working with an Euler-Maruyama discretisation for the diffusion, we use variational inference to jointly learn the parameters and the diffusion paths. We use a standard mean-field variational appr…

This paper reduces labeling costs for meta-learning in wireless systems.

Interpretable deep learning is a fundamental building block towards safer AI, especially when the deployment possibilities of deep learning-based computer-aided medical diagnostic systems are so eminent. However, without a computational formulation of black-box interpretation, general interpretability research rely hea…

Novel Bayesian optimization framework improves portfolio management stability and efficiency.

Proposes a method for explaining black-box models with nested feature attributions.

Unified framework for scalable black-box optimization.

Prediction systems are successfully deployed in applications ranging from disease diagnosis, to predicting credit worthiness, to image recognition. Even when the overall accuracy is high, these systems may exhibit systematic biases that harm specific subpopulations; such biases may arise inadvertently due to underrepre…

This paper uses NLDT to find interpretable control rules from complex DRL policies.

Paper proves conformal prediction works for any data distribution.

New action poisoning attacks improve LinUCB's performance by changing action signals.

While autonomous vehicle (AV) technology has shown substantial progress, we still lack tools for rigorous and scalable testing. Real-world testing, the $\textit{de-facto}$ evaluation method, is dangerous to the public. Moreover, due to the rare nature of failures, billions of miles of driving are needed to statisticall…

With the growing adoption of machine learning techniques, there is a surge of research interest towards making machine learning systems more transparent and interpretable. Various visualizations have been developed to help model developers understand, diagnose, and refine machine learning models. However, a large numbe…