arXiv:2510.15382v2 Announce Type: replace Abstract: The recent development of zero-shot reinforcement learning (RL) has opened a new avenue for learning pre-trained generalist policies that can adapt to arbitrary new tasks in a zero-shot manner. While the popular Forward-Backward representations (FB)…
arXiv:2510.19950v1 Announce Type: new Abstract: In financial applications, reinforcement learning (RL) agents are commonly trained on historical data, where their actions do not influence prices. However, during deployment, these agents trade in live markets where their own transactions can shift…
arXiv:2502.08416v3 Announce Type: replace-cross Abstract: Across many domains of science, stochastic models are an essential tool to understand the mechanisms underlying empirically observed data. Models can be of different levels of detail and accuracy, with models of high-fidelity (i.e., high…
arXiv:2510.19953v1 Announce Type: new Abstract: Zeroth-order optimization (ZOO) is an important framework for stochastic optimization when gradients are unavailable or expensive to compute. A potential limitation of existing ZOO methods is the bias inherent in most gradient estimators unless the…
arXiv:2509.25033v3 Announce Type: replace-cross Abstract: Few-shot learning (FSL) aims to recognize novel concepts from only a few labeled support samples. Recent studies enhance support features by incorporating additional semantic information or designing complex semantic fusion modules. However, they still suffer…
arXiv:2510.19975v1 Announce Type: new Abstract: In this paper, we explore the two-point zeroth-order gradient estimator and identify the distribution of random perturbations that minimizes the estimator’s asymptotic variance as the perturbation stepsize tends to zero. We formulate it as a…
arXiv:2406.05088v2 Announce Type: replace Abstract: The rapid development of time series forecasting research has brought many deep learning-based modules in this field. However, despite the increasing amount of new forecasting architectures, it is still unclear if we have leveraged the…
arXiv:2510.19977v1 Announce Type: new Abstract: Randomized smoothing has become essential for achieving certified adversarial robustness in machine learning models. However, current methods primarily use isotropic noise distributions that are uniform across all data dimensions, such as image pixels, limiting the…
arXiv:2502.19670v2 Announce Type: replace Abstract: In real-world applications, node features in graphs often contain noise from various sources, leading to significant performance degradation in GNNs. Although several methods have been developed to enhance robustness, they rely on the unrealistic assumption…
arXiv:2510.19980v1 Announce Type: new Abstract: Time series forecasting plays a pivotal role in critical domains such as energy management and financial markets. Although deep learning-based approaches (e.g., MLP, RNN, Transformer) have achieved remarkable progress, the prevailing “long-sequence information gain hypothesis”…
