Related papers: Training Gamble leads to Corporate Grumble?
The problem of model collapse has presented new challenges in iterative training of generative models, where such training with synthetic data leads to an overall degradation of performance. This paper looks at the problem from a…
The humble spreadsheet is the most widely used data storage, manipulation and modelling tool. Its ubiquity over the past 30 years has seen its successful application in every area of life. Surprisingly the spreadsheet has remained…
According to a study of The Standish Group International, 44% of software projects cost more and last longer than expected. More accurate the effort estimation is; the better the enterprise gets organized and the more the software project…
Context: When an application evolves, some of the developed test cases break. Discarding broken test cases causes a significant waste of effort and leads to test suites that are less effective and have lower coverage. Test repair approaches…
Microsoft Excel is the most ubiquitous analytical tool ever built. Companies around the world leverage it for its power, flexibility and ease of use. However, spreadsheets are manually intensive and prone to error, making it difficult for…
Practitioners often argue that range names make spreadsheets easier to understand and use, akin to the role of good variable names in traditional programming languages, yet there is no supporting scientific evidence. The authors previously…
Simulated phishing campaigns are widely deployed, yet the behavioral data they produce is endogenous: because training is triggered by clicking, the employees receiving intervention have already demonstrated susceptibility. This…
Spreadsheets provide many of the key links between information systems, closing the gap between business needs and the capability of central systems. Recent regulations have brought these vulnerable parts of information supply chains into…
We demonstrate via several examples how the backward error viewpoint can be used in the analysis of solutions obtained by perturbation methods. We show that this viewpoint is quite general and offers several important advantages. Perhaps…
Automated random testing has shown to be an effective approach to finding faults but still faces a major unsolved issue: how to generate test inputs diverse enough to find many faults and find them quickly. Stateful testing, the automated…
While scientists increasingly recognize the importance of metadata in describing their data, spreadsheets remain the preferred tool for supplying this information despite their limitations in ensuring compliance and quality. Various tools…
Datasets typically contain inaccuracies due to human error and societal biases, and these inaccuracies can affect the outcomes of models trained on such datasets. We present a technique for certifying whether linear regression models are…
Training machine learning models in a meaningful order, from the easy samples to the hard ones, using curriculum learning can provide performance improvements over the standard training approach based on random data shuffling, without any…
While functional programming is an efficient way to express complex software, functional programming languages have a steep learning curve. Haskell can be challenging to learn for students who were only introduced to imperative programming.…
For clinical studies with continuous outcomes, when the data are potentially skewed, researchers may choose to report the whole or part of the five-number summary (the sample median, the first and third quartiles, and the minimum and…
A data analyst might worry about generalization if dropping a very small fraction of data points from a study could change its substantive conclusions. Checking this non-robustness directly poses a combinatorial optimization problem and is…
Computational notebooks became indispensable tools for research-related development, offering unprecedented interactivity and flexibility in the development process. However, these benefits come at the cost of reproducibility and an…
Model errors are pervasive and can be catastrophic. We can reduce model errors and time to market by applying Component-Based Software Engineering (CBSE) concepts to Excel models. CBSE assembles solutions from pre-built, pre-tested…
Denoising Diffusion Probabilistic Models have shown an impressive generation quality, although their long sampling chain leads to high computational costs. In this paper, we observe that a long sampling chain also leads to an error…
Grammar checking is the task of detection and correction of grammatical errors in the text. English is the dominating language in the field of science and technology. Therefore, the non-native English speakers must be able to use correct…