Related papers: Accuracy-Efficiency Trade-Offs and Accountability …

This position paper argues that achieving robustness, privacy, and efficiency simultaneously in machine learning systems is infeasible under prevailing threat models. The tension between these goals arises not from algorithmic shortcomings…

U-statistics play central roles in many statistical learning tools but face the haunting issue of scalability. Significant efforts have been devoted into accelerating computation by U-statistic reduction. However, existing results almost…

Computing accurate deterministic performance bounds is a strong need for communication technologies having strong requirements on latency and reliability. Beyond new scheduling protocols such as TSN, the FIFO policy remains at work within…

When building Deep Learning (DL) models, data scientists and software engineers manage the trade-off between their accuracy, or any other suitable success criteria, and their complexity. In an environment with high computational power, a…

Applications that deal with sensitive information may have restrictions placed on the data available to a machine learning (ML) classifier. For example, in some applications, a classifier may not have direct access to sensitive attributes,…

We study the problem of improving the performance of online algorithms by incorporating machine-learned predictions. The goal is to design algorithms that are both consistent and robust, meaning that the algorithm performs well when…

Research in Responsible AI has developed a range of principles and practices to ensure that machine learning systems are used in a manner that is ethical and aligned with human values. However, a critical yet often neglected aspect of…

As AI agents are increasingly adopted to collaborate on complex objectives, ensuring the security of autonomous multi-agent systems becomes crucial. We develop simulations of agents collaborating on shared objectives to study these security…

Stochastic multi-agent systems are a central modeling framework for autonomous controllers, communication protocols, and cyber-physical infrastructures. In many such systems, however, transition probabilities are only estimated from data…

Many technical approaches have been proposed for ensuring that decisions made by machine learning systems are fair, but few of these proposals have been stress-tested in real-world systems. This paper presents an example of one team's…

Advances in low-communication training algorithms are enabling a shift from centralised model training to compute setups that are either distributed across multiple clusters or decentralised via community-driven contributions. This paper…

Automated decision systems are increasingly used for consequential decision making -- for a variety of reasons. These systems often rely on sophisticated yet opaque models, which do not (or hardly) allow for understanding how or why a given…

In this paper, we investigate the impact of test-time adversarial attacks on linear regression models and determine the optimal level of robustness that any model can reach while maintaining a given level of standard predictive performance…

Decision-making pipelines are generally characterized by tradeoffs among various risk functions. It is often desirable to manage such tradeoffs in a data-adaptive manner. As we demonstrate, if this is done naively, state-of-the art…

Sequential multi-agent systems built with large language models (LLMs) can automate complex software tasks, but they are hard to trust because errors quietly pass from one stage to the next. We study a traceable and accountable pipeline,…

Machine learning (ML) algorithms are increasingly deployed to make critical decisions in socioeconomic applications such as finance, criminal justice, and autonomous driving. However, due to their data-driven and pattern-seeking nature, ML…

Consensus formation is pivotal in multi-agent systems (MAS), balancing collective coherence with individual diversity. Conventional LLM-based MAS primarily rely on explicit coordination, e.g., prompts or voting, risking premature…

Machine learning (ML) systems are increasingly deployed in high-stakes domains where reliability is paramount. This thesis investigates how uncertainty estimation can enhance the safety and trustworthiness of ML, focusing on selective…

Large amounts of electronic medical records collected by hospitals across the developed world offer unprecedented possibilities for knowledge discovery using computer based data mining and machine learning. Notwithstanding significant…

Decentralized learning is an efficient emerging paradigm for boosting the computing capability of multiple bounded computing agents. In the big data era, performing inference within the distributed and federated learning (DL and FL)…