Related papers: Is Hyper-Parameter Optimization Different for Soft…
The paradigm of worst-group loss minimization has shown its promise in avoiding to learn spurious correlations, but requires costly additional supervision on spurious attributes. To resolve this, recent works focus on developing weaker…
To develop software with optimal performance, even small performance changes need to be identified. Identifying performance changes is challenging since the performance of software is influenced by non-deterministic factors. Therefore, not…
With the growth of the open-source data science community, both the number of data science libraries and the number of versions for the same library are increasing rapidly. To match the evolving APIs from those libraries, open-source…
Traditional statistical analysis requires that the analysis process and data are independent. By contrast, the new field of adaptive data analysis hopes to understand and provide algorithms and accuracy guarantees for research as it is…
In the era of data explosion, a growing number of data-intensive computing frameworks, such as Apache Hadoop and Spark, have been proposed to handle the massive volume of unstructured data in parallel. Since programming models provided by…
Spectral risk objectives - also called $L$-risks - allow for learning systems to interpolate between optimizing average-case performance (as in empirical risk minimization) and worst-case performance on a task. We develop stochastic…
A vast amount of valuable data is produced and is becoming available for analysis as a result of advancements in smart cyber-physical systems. The data comes from various sources, such as healthcare, smart homes, smart vehicles, and often…
Privacy-preserving distributed processing has received considerable attention recently. The main purpose of these algorithms is to solve certain signal processing tasks over a network in a decentralised fashion without revealing…
As the interplay between human-generated and synthetic data evolves, new challenges arise in scientific discovery concerning the integrity of the data and the stability of the models. In this work, we examine the role of synthetic data as…
For machine learning datasets to accurately represent diverse opinions in a population, they must preserve variation in data labels while filtering out spam or low-quality responses. How can we balance annotator reliability and…
Smart meters (SMs) can pose privacy threats for consumers, an issue that has received significant attention in recent years. This paper studies the impact of Side Information (SI) on the performance of distortion-based real-time…
Machine Learning (ML) algorithms are vital for supporting clinical decision-making in biomedical informatics. However, their predictive performance can vary across demographic groups, often due to the underrepresentation of historically…
The goal of data-driven algorithm design is to obtain high-performing algorithms for specific application domains using machine learning and data. Across many fields in AI, science, and engineering, practitioners will often fix a family of…
Large language models achieve high performance on many but not all downstream tasks. The interaction between pretraining data and task data is commonly assumed to determine this variance: a task with data that is more similar to a model's…
While statistics focusses on hypothesis testing and on estimating (properties of) the true sampling distribution, in machine learning the performance of learning algorithms on future data is the primary issue. In this paper we bridge the…
Synthetic tabular data enables sharing and analysis of sensitive records, but its practical deployment requires balancing distributional fidelity, downstream utility, and privacy protection. We study a simple, model agnostic post processing…
Code super-optimization is the task of transforming any given program to a more efficient version while preserving its input-output behaviour. In some sense, it is similar to the paraphrase problem from natural language processing where the…
Machine learning algorithms have been used widely in various applications and areas. To fit a machine learning model into different problems, its hyper-parameters must be tuned. Selecting the best hyper-parameter configuration for machine…
Estimating statistical models within sensor networks requires distributed algorithms, in which both data and computation are distributed across the nodes of the network. We propose a general approach for distributed learning based on…
In open-source software development environments; textual, numerical and relationship-based data generated are of interest to researchers. Various data sets are available for this data, which is frequently used in areas such as software…