This work focuses on the finite-sample regime, quantifying how well a designer can approximate any point on the FA frontier from limited data and bounding the worst-case gap, and derives worst-case-optimal estimators that depend on the designer's knowledge of the covariate distribution.
Alireza Fallah, Michael I. Jordan, Annie Ulichney· arXiv.org· 2 citations
This work develops an epoch-based reinforcement learning algorithm for infinite-horizon average-cost MDPs with continuous state and action spaces that exploits this order through counterfactual inference and instantiates the framework in lost-sales inventory systems with positive lead times, dual-sourcing systems gover...
Zhongju Zhang, Shipra Agrawal, Ilan Lobel et al.· arXiv.org· 1 citation
Handling missing values is a common challenge in biostatistical analyses, typically addressed by imputation methods. We propose a novel, fast, and easy-to-use imputation method called missing value imputation with adversarial random forests (MissARF), based on generative machine learning, that provides both single and...
Pegah Golchian, Jan Kapar, David S. Watson et al.· 0 citations
Causal Bayesian networks are often described as causal because they support reasoning about interventions. Yet interventions are defined in the mathematical model, whereas the resulting model predictions concern the effects of actions in the real world. Consequently, whether and how a causal model makes falsifiable pre...
Frederik Hytting J{\o}rgensen, Luigi Gresele, Sebastian Weichwald· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
We introduce an ordinary differential equation (ODE) based deep generative method for learning conditional distributions, named Conditional F\"ollmer Flow. Starting from a standard Gaussian distribution, the proposed flow could approximate the target conditional distribution very well when the time is close to 1. For e...
Jinyuan Chang, Zhao Ding, Yuling Jiao et al.· 0 citations
Entropy reduction is not a safety criterion: it can leave predictions unchanged or accompany increasing risk for a protected group. We study entropy-regulated learning under separately specified task, risk, and intervention constraints. A noise-calibrated log-determinant functional yields an exact spectral force formul...
Published transfer-BO comparisons often estimate an average treatment effect of acquisition choice over hidden regime variables, while practitioners need the conditional effect for their specific prior quality, budget ratio, and metric. An audit of 40 transfer-BO papers from NeurIPS, ICML, ICLR, AISTATS, UAI, TMLR, JML...
We consider minimising a spectral risk objective, the expected cost plus a weighted conditional value-at-risk, when the distribution of the uncertain parameters depends on the decision and can only be sampled through a stochastic simulator under a fixed budget of draws. We propose adaptive conditional residual sampling...
Machine learning models perform well across domains such as diagnostics, weather forecasting, NLP, and autonomous driving, but their limited uncertainty handling restricts use in safety-critical settings. Traditional neural networks often fail to detect out-of-domain (OOD) data and may output confident yet incorrect pr...
Bernhard Klein, Falk Selker, Hendrik Borras et al.· 0 citations
Path reasoning graph neural networks have demonstrated state-of-the-art performance on knowledge graph completion tasks such as link prediction. However, interpreting their predictions remains a challenging open problem, as most GNN explainability methods target node-level or graph-level tasks. In this paper, we propos...
The policy gradient theorem describes the gradient of the expected discounted return with respect to an agent's policy parameters. However, many policy gradient methods omit the outer discount factor, yielding an update that need not equal the gradient of the discounted objective. Is the resulting update the gradient o...
The evidence, $\mathcal{Z} = p(x | \mathcal{M})$, of a data-generating model $\mathcal{M}$ is a powerful tool in Bayesian frameworks: it enables model inference, model misspecification tests, and goodness-of-fit assessment as an alternative to standard discrepancy statistics, e.g. $\chi^2$. While versatile, the evidenc...
Kai Lehman, Jameson Dong, Carolina Cuesta-Lazaro et al.· 0 citations
Is your company’s AI sovereign? A practical guide for CIOs on AI vendor lock-in, EU Data Act switching, cloud sovereignty, and testing your exit plan before you need it. The post Sovereignty Is the Option to Leave appeared first on GPT-Lab.
