arXiv:2604.10202v2 Announce Type: replace Abstract: Neural networks (NNs) are central to modern machine learning and achieve state-of-the-art results in many applications. However, the relationship between loss geometry and generalization is still not well understood. The local geometry of the loss…
arXiv:2604.11944v1 Announce Type: new Abstract: Diabetes devices, including Continuous Glucose Monitoring (CGM), Smart Insulin Pens, and Automated Insulin Delivery systems, generate rich time-series data widely used in research and machine learning. However, inconsistent data formats across sources hinder sharing, integration,…
arXiv:2505.23737v2 Announce Type: replace-cross Abstract: The majority of parameters in neural networks are naturally represented as matrices. However, most commonly used optimizers treat these matrix parameters as flattened vectors during optimization, potentially overlooking their inherent structural properties. Recently, an optimizer…
arXiv:2604.11945v1 Announce Type: new Abstract: High-fidelity numerical simulation of subsurface flow is computationally intensive, especially for many-query tasks such as uncertainty quantification and data assimilation. Deep learning (DL) surrogates can significantly accelerate forward simulations, yet constructing them requires substantial machine…
arXiv:2602.05971v2 Announce Type: replace-cross Abstract: Semantic representations can be framed as a structured, dynamic knowledge space through which humans navigate to retrieve and manipulate meaning. To investigate how humans traverse this geometry, we introduce a framework that represents concept production…
arXiv:2604.11947v1 Announce Type: new Abstract: Unlocking large-scale low-bandwidth decentralized training has the potential to utilize otherwise untapped compute resources. In centralized settings, large-scale multi-node training is primarily enabled by data and pipeline parallelism, two techniques that require ultra-high-bandwidth communication. While…
arXiv:2604.10911v2 Announce Type: replace-cross Abstract: Medium- to long-horizon equity allocation is challenging due to weak predictive structure, non-stationary market regimes, and the degradation of signals under realistic trading constraints. Conventional approaches often rely on single predictors or loosely coupled pipelines,…
arXiv:2604.11948v1 Announce Type: new Abstract: Large Foundation Model (LFM) inference is both memory- and compute-intensive, traditionally relying on GPUs. However, the limited availability and high cost have motivated the adoption of high-performance general-purpose CPUs, especially emerging 3D-stacked Static Non-Uniform Cache…
arXiv:2604.12737v1 Announce Type: cross Abstract: While Federated Learning (FL) mitigates direct data exposure, the resulting trained models remain susceptible to membership inference attacks (MIAs). This paper presents an empirical evaluation of Differential Privacy (DP) as a defense mechanism against MIAs…
arXiv:2604.11962v1 Announce Type: new Abstract: Identifying and understanding the features that a deep network (DN) extracts from its inputs to produce its outputs is a focal point of interpretability research. The Linear Representation Hypothesis (LRH) identifies features in terms of…
