digitado

arXiv:2604.00553v1 Announce Type: new Abstract: The scenario approach provides a powerful data-driven framework for designing solutions under uncertainty with rigorous probabilistic robustness guarantees. Existing theory, however, primarily addresses assessing robustness with respect to a single appropriateness criterion for the solution based on a dataset, whereas many practical applications – including multi-agent decision problems – require the simultaneous consideration of multiple criteria and the assessment of their robustness based on multiple datasets, one per criterion. This paper develops a […]

Ver mais

arXiv:2604.00432v1 Announce Type: new Abstract: We study the problem of reconstructing the latent geometry of a $d$-dimensional Riemannian manifold from a random geometric graph. While recent works have made significant progress in manifold recovery from random geometric graphs, and more generally from noisy distances, the precision of pairwise distance estimation has been fundamentally constrained by the volumetric barrier, namely the natural sample-spacing scale $n^{-1/d}$ coming from the fact that a generic point of the manifold typically lies at […]

Ver mais

arXiv:2604.00064v1 Announce Type: new Abstract: We study trajectory forecasting under squared loss for time series with weak conditional structure, using highly expressive prediction models. Building on the classical characterization of squared-loss risk minimization, we emphasize regimes in which the conditional expectation of future trajectories is effectively degenerate, leading to trivial Bayes-optimal predictors (flat for prices and zero for returns in standard financial settings). In this regime, increased model expressivity does not improve predictive accuracy but instead introduces spurious […]

Ver mais

arXiv:2604.00038v1 Announce Type: new Abstract: In Part I of this series, we established a rigorous mathematical isomorphism between ant colony decision-making and random forest learning, demonstrating that variance reduction through decorrelation is a universal principle shared by biological and computational ensembles. Here we turn to the complementary mechanism: bias reduction through adaptive weighting. Just as boosting algorithms sequentially focus on difficult instances, ant colonies dynamically amplify successful foraging paths through pheromone-mediated recruitment. We prove that these processes are […]

Ver mais

arXiv:2603.28873v2 Announce Type: new Abstract: Humans learn and form memories in stochastic environments. Auto-associative memory systems model these processes by storing patterns and later recovering them from corrupted versions. Here, memories are learned by associating each pattern with an attractor in a latent space. After learning, when (possibly corrupted) patterns are presented to the system, latent dynamics facilitate retrieval of the appropriate uncorrupted pattern. In this work, we propose a novel online auto-associative memory system. In contrast to […]

Ver mais

inter-related concepts: Q, pi, v, G This seems simple at first but quite confusing. The return is a way to talk about the long term and probabilistic nature of rewards. We can use return to assign values to both states and actions at a particular state, v(s), Q(s, a) respectively. But in Q, the action and state are inter-related already. The concept of policy pi encapsulates this relation. In the beginning, we may not have any knowledge of […]

Ver mais

Electrocardiograms (ECGs) are among the most widely used diagnostic tools for cardiovascular diseases, and a large amount of ECG data worldwide appears only in image form. However, most existing automated ECG analysis methods rely on access to raw signal recordings, limiting their applicability in real-world and resource-constrained settings. In this paper, we present ECG-Scan, a self-supervised framework for learning clinically generalized representations from ECG images through dual physiological-aware alignments: 1) Our approach optimizes image representation learning using multimodal […]

Ver mais

Hello everyone, I’m building a RL project around Monster Hunter Tri running in Dolphin, and I’m hitting a set of problems that feel very close to partial observability / state estimation rather than “just” policy learning. The setup is hybrid: – memory reads for player state and environment context, – heuristic detection when memory is incomplete, – an octree/cube-based spatial approximation, – and eventually more vision-based signals. The biggest issue is monster state. I can get some usable […]

Ver mais