technocracy

The Rashomon set captures the collection of models that achieve near-identical empirical performance yet may differ substantially in their decision boundaries. Understanding the differences among these models, i.e., their multiplicity, is recognized as a crucial step toward model transparency, fairness, and robustness, as it reveals decision boundaries instabilities that standard metrics obscure. However, the existing definitions of Rashomon set and multiplicity metrics assume centralized learning and do not extend naturally to decentralized, multi-party settings like Federated Learning (FL). […]

Ver mais

arXiv:2603.05648v1 Announce Type: new Abstract: Join patterns are a high-level programming construct for message-passing applications. They offer an intuitive and declarative approach for specifying how concurrent and distributed components coordinate, possibly depending on complex conditions over combinations of messages. Join patterns have inspired many implementations — but most of them are not available as libraries: rather, they are domain-specific languages that can be hard to integrate into pre-existing ecosystems. Moreover, all implementations ship with a predefined matching algorithm, […]

Ver mais

Objective: Accurate noninvasive estimation of intracranial pressure (ICP) remains a major challenge in critical care. We developed a bespoke machine learning algorithm that integrates system identification and ranking-constrained optimization to estimate mean ICP from noninvasive signals. Methods: A machine learning framework was proposed to obtain accurate mean ICP values using arbitrary noninvasive signals. The subspace system identification algorithm is employed to identify cerebral hemodynamics models for ICP simulation using arterial blood pressure (ABP), cerebral blood velocity (CBv), and […]

Ver mais

arXiv:2604.13037v1 Announce Type: new Abstract: Mining multiple longest common subsequences (textit{MLCS}) from a set of sequences of three or more over a finite alphabet $Sigma$ (a classical NP-hard problem) is an important task in a wide variety of application fields. Unfortunately, there is still no exact textit{MLCS} algorithm/tool that can handle long (length $ge$ 1,000) or big (length $ge$ 10,000) sequences, which seriously hinders the development and utilization of massive long or big sequences from various application fields […]

Ver mais

arXiv:2603.02343v1 Announce Type: new Abstract: This paper introduces Pulli Kolam, a traditional South Indian craft, as a medium for physical data representation. Grounded in its cultural meaning and embodied practice, Pulli Kolam follows structured geometric rules while allowing creative variation. We identify five mapping strategies within Kolam (dots, patterns, fills, lines, and color) that can be used for representing data physically. without disrupting traditional practice. Through an illustrative scenario of daily well-being tracking, we demonstrate how data representation […]

Ver mais

Machine unlearning is rapidly becoming a practical requirement, driven by privacy regulations, data errors, and the need to remove harmful or corrupted training samples. Despite this, most existing methods tackle the problem purely from a post-hoc perspective. They attempt to erase the influence of targeted training samples through parameter updates that typically require access to the full training data. This creates a mismatch with real deployment scenarios where unlearning requests can be anticipated, revealing a fundamental limitation of […]

Ver mais

Rehearsal is one of the key techniques for mitigating catastrophic forgetting and has been widely adopted in continual learning algorithms due to its simplicity and practicality. However, the theoretical understanding of how rehearsal scale influences learning dynamics remains limited. To address this gap, we formulate rehearsal-based continual learning as a multidimensional effectiveness-driven iterative optimization problem, providing a unified characterization across diverse performance metrics. Within this framework, we derive a closed-form analysis of adaptability, memorability, and generalization from the […]

Ver mais

Tested on: RTX 5060 · PyTorch 2.7 · CUDA 13.1 · Windows 11 You moved your model to the GPU. You watched nvidia-smi climb toward 100%. You assumed you were done. You probably aren’t. GPU utilization is a coarse, 100ms-sampled metric. A GPU can report 80% utilization while spending most of that time idle between kernels, starved by a DataLoader that can’t keep up, or stalled waiting for your Python code to read a loss value. We’ll cover […]

Ver mais

arXiv:2603.20242v1 Announce Type: new Abstract: Many speech enhancement (SE) methods rely on continuous representations. Recently, discrete audio tokens have been explored to enable autoregressive generation for SE. However, it remains unclear whether discretization itself consistently improves SE performance. In this paper, we introduce LL-SDR, a token-based speech enhancement framework that explicitly leverages discretization to better separate speech and noise. Our first contribution is a Variance-Ordered Residual Vector Quantizer (VO-RVQ), designed to disentangle speech and noise distributions during tokenization. […]

Ver mais