Related papers: Learning Surrogate Models of Document Image Qualit…

The paper proposes and investigates an approach for surrogate-assisted performance prediction of data-driven knowledge discovery algorithms. The approach is based on the identification of surrogate models for prediction of the target…

Surrogate models are used to reduce the burden of expensive-to-evaluate objective functions in optimization. By creating models which map genomes to objective values, these models can estimate the performance of unknown inputs, and so be…

Surrogate models have several uses in engineering design, including speeding up design optimization, noise reduction, test measurement interpolation, gradient estimation, portability, and protection of intellectual property. Traditionally,…

Offline optimization is an important task in numerous material engineering domains where online experimentation to collect data is too expensive and needs to be replaced by an in silico maximization of a surrogate of the black-box function.…

Mammographic screening is an effective method for detecting breast cancer, facilitating early diagnosis. However, the current need to manually inspect images places a heavy burden on healthcare systems, spurring a desire for automated…

Numerical solutions of partial differential equations (PDEs) require expensive simulations, limiting their application in design optimization, model-based control, and large-scale inverse problems. Surrogate modeling techniques seek to…

Tuning parameters of a non-differentiable or black-box compute is challenging. Existing methods rely mostly on random sampling or grid sampling from the parameter space. Further, with all the current methods, it is not possible to supply…

Diffusion models have emerged as powerful priors for image editing tasks such as inpainting and local modification, where the objective is to generate realistic content that remains consistent with observed regions. In particular, zero-shot…

A world model creates a surrogate world to train a controller and predict safety violations by learning the internal dynamic model of systems. However, the existing world models rely solely on statistical learning of how observations change…

Recent works in learning-integrated optimization have shown promise in settings where the optimization problem is only partially observed or where general-purpose optimizers perform poorly without expert tuning. By learning an optimizer…

Recently, several optimization methods have been successfully applied to the hyperparameter optimization of deep neural networks (DNNs). The methods work by modeling the joint distribution of hyperparameter values and corresponding error.…

Metafeatures, or dataset characteristics, have been shown to improve the performance of hyperparameter optimization (HPO). Conventionally, metafeatures are precomputed and used to measure the similarity between datasets, leading to a better…

Document image classification is different from plain-text document classification and consists of classifying a document by understanding the content and structure of documents such as forms, emails, and other such documents. We show that…

Surrogate models are widely used to approximate complex systems across science and engineering to reduce computational costs. Despite their widespread adoption, the field lacks standardisation across key stages of the modelling pipeline,…

We present a framework for automatically structuring and training fast, approximate, deep neural surrogates of stochastic simulators. Unlike traditional approaches to surrogate modeling, our surrogates retain the interpretable structure and…

Recent developments of advanced driver-assistance systems necessitate an increasing number of tests to validate new technologies. These tests cannot be carried out on track in a reasonable amount of time and automotive groups rely on…

This study investigates the robustness of image classifiers to text-guided corruptions. We utilize diffusion models to edit images to different domains. Unlike other works that use synthetic or hand-picked data for benchmarking, we use…

We introduce CODES, a benchmark for comprehensive evaluation of surrogate architectures for coupled ODE systems. Besides standard metrics like mean squared error (MSE) and inference time, CODES provides insights into surrogate behaviour…

In this paper, we address the well-known image quality assessment problem but in contrast from existing approaches that predict image quality independently for every images, we propose to jointly model different images depicting the same…

In this paper, we propose an iterative framework, which consists of two phases: a generation phase and a training phase, to generate realistic training data and yield a supervised homography network. In the generation phase, given an…