Related papers: Mind the hubris: complexity can misfire
Machine learning models in safety-critical settings like healthcare are often blackboxes: they contain a large number of parameters which are not transparent to users. Post-hoc explainability methods where a simple, human-interpretable…
Model uncertainty is a crucial issue in statistics, econometrics and machine learning, yet its definition remains ambiguous and is subject to various interpretations in the literature. So far, there has not been a universally accepted…
Causal questions often permeate in our day-to-day activities. With causal reasoning and counterfactual intuition, privacy threats can not only be alleviated but also prevented. In this paper, we discuss what is causal and counterfactual…
The increasing availability of advanced computational modelling offers new opportunities to improve safety, efficacy, and emissions reductions. Application of complex models to support engineering decisions has been slow in comparison to…
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…
Familiarity with a simulation platform can seduce modellers into accepting untested assumptions for convenience of implementation. These assumptions may have consequences greater than commonly suspected, and it is important that modellers…
While recent foundation models have enabled significant breakthroughs in monocular depth estimation, a clear path towards safe and reliable deployment in the real-world remains elusive. Metric depth estimation, which involves predicting…
Model extraction increasingly attracts research attentions as keeping commercial AI models private can retain a competitive advantage. In some scenarios, AI models are trained proprietarily, where neither pre-trained models nor sufficient…
Recent decisions by leading AI labs to either open-source their models or to restrict access to their models has sparked debate about whether, and how, increasingly capable AI models should be shared. Open-sourcing in AI typically refers to…
Mathematics cannot anymore be assimilated to a linguistic game, where formal proofs are strongly differentiated with conjectural thinking, without building any category of knowledge to understand the passage (Wittgenstein's gist). Nowadays,…
In model-based reinforcement learning, planning with an imperfect model of the environment has the potential to harm learning progress. But even when a model is imperfect, it may still contain information that is useful for planning. In…
The classical view of epistemic logic is that an agent knows all the logical consequences of their knowledge base. This assumption of logical omniscience is often unrealistic and makes reasoning computationally intractable. One approach to…
Organisations, whether in government, industry or commerce, are required to make decisions in a complex and uncertain environment. The way models are used is intimately connected to the way organisations make decisions and the context in…
In recent years, the use of sophisticated statistical models that influence decisions in domains of high societal relevance is on the rise. Although these models can often bring substantial improvements in the accuracy and efficiency of…
The Weltanschauung emerging from quantum theory clashes profoundly with our classical concepts. Quantum characteristics like superposition, entanglement, wave-particle duality, nonlocality, contextuality are difficult to reconcile with our…
Uncertainty quantification (UQ) is a vital step in using mathematical models and simulations to take decisions. The field of cardiac simulation has begun to explore and adopt UQ methods to characterise uncertainty in model inputs and how…
A variety of techniques have been proposed to train machine learning classifiers that are independent of a given feature. While this can be an essential technique for enabling background estimation, it may also be useful for reducing…
Shojaee et al. (2025) report that Large Reasoning Models (LRMs) exhibit "accuracy collapse" on planning puzzles beyond certain complexity thresholds. We demonstrate that their findings primarily reflect experimental design limitations…
Coupled natural systems are generally modeled at multiple abstraction levels. Both structural scale and behavioral complexity of these models are determinants in the kinds of questions that can be posed and answered. As scale and complexity…
To steer language models towards truthful outputs on tasks which are beyond human capability, previous work has suggested training models on easy tasks to steer them on harder ones (easy-to-hard generalization), or using unsupervised…