arXiv:2606. 14648v1 Announce Type: new Abstract: Robust machine learning and optimization rely on the uncertainty model choice.
arXiv:2510. 07750v3 Announce Type: replace-cross Abstract: Robust optimization safeguards decisions against uncertainty by optimizing against worst-case scenarios, yet their effectiveness hinges on a prespecified robustness level that is often chosen ad hoc, leading to either insufficient protection or overly conservative and costly solutions.
arXiv:2404. 03578v3 Announce Type: replace Abstract: The sim-to-real gap, which represents the disparity between training and testing environments, poses a significant challenge in reinforcement learning (RL).
arXiv:2606. 00002v1 Announce Type: new Abstract: Mixed-Integer Linear Programming (MILP) decision engines routinely output nominally optimal plans for high-stakes industrial systems.
arXiv:2505. 04757v2 Announce Type: replace Abstract: This paper introduces a novel approach to contextual stochastic optimization, integrating operations research and machine learning to address decision-making under uncertainty.
arXiv:2607. 24983v1 Announce Type: cross Abstract: Generative models are increasingly adopted in distributionally robust optimization (DRO), but existing approaches trade off model compatibility and adversarial structure: methods that accept arbitrary samplers do not restrict worst-case laws to a generator family, while generator-parameterized adversaries rely on model-specific access such as likelihoods, scores, or training data.
arXiv:2606. 07954v1 Announce Type: cross Abstract: Training large language models (LLMs) on heterogeneous data requires selecting minibatches that balance convergence speed with coverage across domains.
arXiv:2605. 30089v2 Announce Type: replace Abstract: Standard Set Representation Learning methods typically excel on curated data but often overlook the challenge of inference-time element corruption.
arXiv:2606. 10734v1 Announce Type: new Abstract: Conformal Prediction (CP) provides robust uncertainty guarantees for predictive models, but is typically applied post hoc, which misaligns model training with the conformal goal of producing efficient (i.
arXiv:2607. 11555v1 Announce Type: new Abstract: Learning neural set functions is pivotal to a wide range of important applications, including compound selection in AI-driven drug discovery and product recommendation.
arXiv:2608. 04057v1 Announce Type: cross Abstract: Top-$k$ selection determines which components of a sparse model remain active.
arXiv:2607. 03860v1 Announce Type: new Abstract: The Strong Lottery Ticket Hypothesis (SLTH) asserts that sufficiently overparameterized, randomly initialized neural networks contain sparse subnetworks that, even without any training, can match the performance of a small trained network on a given dataset.
arXiv:2607. 05536v1 Announce Type: cross Abstract: Randomized smoothing has emerged as a scalable technique for certifying the adversarial robustness of classifiers.