arXiv:2511.08789v1 Announce Type: new Abstract: The bias-variance decomposition is a central result in statistics and machine learning, but is typically presented only for the squared error. We present a generalization of the bias-variance decomposition where the prediction error is a…
arXiv:2511.09558v1 Announce Type: cross Abstract: Large Vision Models trained on internet-scale data have demonstrated strong capabilities in segmenting and semantically understanding object parts, even in cluttered, crowded scenes. However, while these models can direct a robot toward the general region…
arXiv:2511.08821v1 Announce Type: new Abstract: We present BayesQ, an uncertainty-guided post-training quantization framework that is the first to optimize quantization under the posterior expected loss. BayesQ fits a lightweight Gaussian posterior over weights (diagonal Laplace by default; optional K-FAC/low-rank), whitens…
arXiv:2502.08083v2 Announce Type: replace Abstract: Graph neural networks (GNNs) have achieved significant progress in graph-based learning tasks, yet their performance often deteriorates when facing heterophilous structures where connected nodes differ substantially in features and labels. To address this limitation, we…
arXiv:2511.08831v1 Announce Type: new Abstract: In the design and operation of complex dynamical systems, it is essential to ensure that all state trajectories of the dynamical system converge to a desired equilibrium within a guaranteed stability region. Yet, for many…
arXiv:2505.22224v2 Announce Type: replace Abstract: Mathematical optimization is a fundamental tool for decision-making in a wide range of applications. However, in many real-world scenarios, the parameters of the optimization problem are not known a priori and must be predicted from…
arXiv:2511.08832v1 Announce Type: new Abstract: In this paper, we propose capturing and utilizing textit{Temporal Information through Graph-based Embeddings and Representations} or textbf{TIGER} to enhance multi-agent reinforcement learning (MARL). We explicitly model how inter-agent coordination structures evolve over time. While most…
arXiv:2510.03669v3 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards has significantly advanced the reasoning capabilities of large language models, yet how to explicitly steer training toward exploration or exploitation remains an open problem. We introduce Token Hidden Reward (THR),…
arXiv:2511.08841v1 Announce Type: new Abstract: Differentially Private Stochastic Gradient Descent (DPSGD) is widely used to train deep neural networks with formal privacy guarantees. However, the addition of differential privacy (DP) often degrades model accuracy by introducing both noise and bias.…
arXiv:2511.08243v2 Announce Type: replace Abstract: The Transformer architecture has achieved tremendous success in natural language processing, computer vision, and scientific computing through its self-attention mechanism. However, its core components-positional encoding and attention mechanisms-have lacked a unified physical or mathematical interpretation.…
