arXiv:2507.09905v3 Announce Type: replace-cross Abstract: In multi-source learning with discrete labels, distributional heterogeneity across domains poses a central challenge to developing predictive models that transfer reliably to unseen domains. We study multi-source unsupervised domain adaptation, where labeled data are available from multiple source domains and only unlabeled data are observed from the target domain. To address potential distribution shifts, we propose a novel Conditional Group Distributionally Robust Optimization (CG-DRO) framework that learns a classifier by minimizing the worst-case […]

Ver mais

arXiv:2505.23783v3 Announce Type: replace Abstract: In-Context Learning (ICL) allows Large Language Models (LLMs) to adapt to new tasks with just a few examples, but their predictions often suffer from systematic biases, leading to unstable performance in classification. While calibration techniques are proposed to mitigate these biases, we show that, in the logit space, many of these methods are equivalent to merely shifting the LLM’s decision boundary without having the ability to alter its orientation. This proves inadequate when […]

Ver mais

arXiv:2602.13311v1 Announce Type: new Abstract: In industrial millimeter-wave (mmWave) multi-hop Integrated Access and Backhaul (IAB) networks, dynamic blockages caused by moving obstacles pose a severe threat to robust and continuous networks. While Packet Duplication (PD) enhances reliability by path diversity, it inevitably doubles the traffic load, leading to severe congestion and degraded Age of Information (AoI). To navigate this reliability-congestion trade-off, we formulated an optimization problem in a multi-hop IAB scenario that minimizes the average AOI while satisfying […]

Ver mais

arXiv:2601.02411v1 Announce Type: new Abstract: Time-series forecasting often operates under tight power and latency budgets in fields like traffic management, industrial condition monitoring, and on-device sensing. These applications frequently require near real-time responses and low energy consumption on edge devices. Spiking neural networks (SNNs) offer event-driven computation and ultra-low power by exploiting temporal sparsity and multiplication-free computation. Yet existing SNN-based time-series forecasters often inherit complex transformer blocks, thereby losing much of the efficiency benefit. To solve the problem, […]

Ver mais

We introduce a Monte Carlo (MC) dataset of single- and two-track drift chamber events to advance Machine Learning (ML)-based track reconstruction. To enable standardized and comparable evaluation, we define track reconstruction specific metrics and report results for traditional track reconstruction algorithms and a Graph Neural Networks (GNNs) method, facilitating rigorous, reproducible validation for future research.

Ver mais

arXiv:2604.07393v1 Announce Type: new Abstract: Accurate forecasting of industrial time series requires balancing predictive accuracy with physical plausibility under non-stationary operating conditions. Existing data-driven models often achieve strong statistical performance but struggle to respect regime-dependent interaction structures and transport delays inherent in real-world systems. To address this challenge, we propose DSPR (Dual-Stream Physics-Residual Networks), a forecasting framework that explicitly decouples stable temporal patterns from regime-dependent residual dynamics. The first stream models the statistical temporal evolution of individual variables. […]

Ver mais

arXiv:2604.18810v1 Announce Type: new Abstract: An algorithm for simulation of switching converters is proposed in the paper. The algorithm is based on simulation of averaged circuit model applying “switching cell” concept, and construction of instantaneous values of the waveforms using quasi steady state and linear ripple approximation. Simulation covers converters operating both in the continuous and the discontinuous conduction mode. Application of the algorithm is demonstrated by simulation results of all three of the basic converters: buck, boost […]

Ver mais

I am working on an RL-based trading system where the agent does more than just predict price direction — it learns portfolio allocation across 6 assets, stop-losses, take-profits, and other trade management decisions. I have been thinking about adding a second model, maybe a transformer or some other suitable architecture, trained on the same 1-hour OHLCV data and possibly auxiliary features, but with a much simpler job: predict only the next price move or just up/down direction. Then […]

Ver mais

arXiv:2601.21739v1 Announce Type: cross Abstract: Adam has been at the core of large-scale training for almost a decade, yet a simple empirical fact remains unaccounted for: both validation scores and the qualitative behaviour of the training runs improve when the momentum parameters satisfy $beta_{1}=beta_{2}$. Some recent studies have reported this pattern, but there is still no explanation for why this choice helps. We show that this choice is closely tied to a structural property that we refer to […]

Ver mais