arXiv:2510.17486v2 Announce Type: replace Abstract: We introduce a methodology for analyzing neural networks through the lens of layer-wise Hessian matrices. The local Hessian of each functional block (layer) is defined as the matrix of second derivatives of a scalar function…
arXiv:2407.10807v2 Announce Type: replace-cross Abstract: Tabular data is considered the last unconquered castle of deep learning, yet the task of data stream classification is stated to be an equally important and demanding research area. Due to the temporal constraints, it…
arXiv:2504.00467v2 Announce Type: replace Abstract: This paper presents the Min-Cut Bayesian Network Consensus (MCBNC) algorithm, a greedy method for structural consensus of Bayesian Networks (BNs), with applications in federated learning and model aggregation. MCBNC prunes weak edges from an initial…
arXiv:2507.23534v2 Announce Type: replace Abstract: Continual learning (CL) seeks to mitigate catastrophic forgetting when models are trained with sequential tasks. A common approach, experience replay (ER), stores past exemplars but only sparsely approximates the data distribution, yielding fragile and oversimplified…
arXiv:2511.07139v1 Announce Type: cross Abstract: Vector data trading is essential for cross-domain learning with vector databases, yet it remains largely unexplored. We study this problem under online learning, where sellers face uncertain retrieval costs and buyers provide stochastic feedback to…
arXiv:2402.12727v2 Announce Type: replace Abstract: Diffusion models are a remarkably effective way of learning and sampling from a distribution $p(x)$. In posterior sampling, one is also given a measurement model $p(y mid x)$ and a measurement $y$, and would like…
arXiv:2511.05569v1 Announce Type: new Abstract: Accurate forecasting of jet fuel demand is crucial for optimizing supply chain operations in the aviation market. Fuel distributors specifically require precise estimates to avoid inventory shortages or excesses. However, there is a lack of…
arXiv:2511.06645v1 Announce Type: cross Abstract: The rapid adoption of large language models (LLMs), such as GPT-4 and Claude 3.5, underscores the need to distinguish LLM-generated text from human-written content to mitigate the spread of misinformation and misuse in education. One…
arXiv:2511.05563v1 Announce Type: new Abstract: Masked Diffusion Models (MDMs) as language models generate by iteratively unmasking tokens, yet their performance crucially depends on the inference time order of unmasking. Prevailing heuristics, such as confidence based sampling, are myopic: they optimize…
arXiv:2511.05568v1 Announce Type: new Abstract: Distribution shifts and minority subpopulations frequently undermine the reliability of deep neural networks trained using Empirical Risk Minimization (ERM). Distributionally Robust Optimization (DRO) addresses this by optimizing for the worst-case risk within a neighborhood of…
