We study the distribution of regret in stochastic multi-armed bandits and episodic reinforcement learning through a unified framework. We formalize a distributional regret bound as a probabilistic guarantee that holds uniformly over all confidence levels $δin (0,1]$, thereby characterizing the regret distribution across the full range of $δ$. We present a simple UCBVI-style algorithm with exploration bonus $min{c_{1,k}/N, c_{2,k}/sqrt{N}}$, where $N$ denotes the visit count and $(c_{1,k},c_{2,k})$ are user-specified parameters. For arbitrary parameter sequences, we derive general gap-independent […]

Ver mais

Hey everyone, hope this is ok to post here. I built a free EU AI Act risk assessment tool and would love some feedback from people who actually know this space. You fill out a 10-question form describing your AI system, it classifies your EU AI Act risk tier, and emails you a PDF report with your applicable Articles and priority actions. Takes about 2 minutes, no account required. https://assessment.aiella.com Eventually I want to build a monitoring SDK […]

Ver mais

arXiv:2603.20254v1 Announce Type: new Abstract: Student experiences and empirical studies report that “black box” AI text detectors produce high false positive rates with disproportionate errors against certain student populations, yet typically theoretical analyses model detection as a test between two known distributions for human and AI prose. This framing omits the structural feature of university assessment whereby an assessor generally does not know the individual student’s writing distribution, making the null hypothesis composite. Standard application of the variational […]

Ver mais

Discovery of sensitive and biologically grounded biomarkers is essential for early detection and monitoring of Alzheimer’s disease (AD). Structural MRI is widely available but typically relies on hand-crafted features such as cortical thickness or volume. We ask whether self-supervised learning (SSL) can uncover more powerful biomarkers from the same data. Existing SSL methods underperform FreeSurfer-derived features in disease classification, conversion prediction, and amyloid status prediction. We introduce Residual Noise Contrastive Estimation (R-NCE), a new SSL framework that integrates […]

Ver mais

A primary goal of online deliberation platforms is to identify ideas that are broadly agreeable to a community of users through their expressed preferences. Yet, consensus elicitation should ideally extend beyond the specific statements provided by users and should incorporate the relative salience of particular topics. We address this issue by modelling consensus as an interval in a one-dimensional opinion space derived from potentially high-dimensional data via embedding and dimensionality reduction. We define an objective that maximizes expected […]

Ver mais

arXiv:2604.07361v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have been widely used in diverse brain network analysis tasks based on preprocessed functional magnetic resonance imaging (fMRI) data. However, their performances are constrained due to high feature sparsity and inherent limitations of domain knowledge within uni-modal neurographs. Meanwhile, large language models (LLMs) have demonstrated powerful representation capabilities. Combining LLMs with GNNs presents a promising direction for brain network analysis. While LLMs and MLLMs have emerged in neuroscience, integration […]

Ver mais