arXiv:2510.08539v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR), which uses simple binary feedback to post-train large language models, has shown significant empirical success. However, a principled understanding of why it works has been lacking. This paper builds…
arXiv:2510.08573v1 Announce Type: cross Abstract: We construct a neural network to perform regression on the local dark-matter density field given line-of-sight peculiar velocities of dark-matter halos, biased tracers of the dark matter field. Our architecture combines a convolutional U-Net with…
arXiv:2510.07525v1 Announce Type: cross Abstract: Independent Component Analysis (ICA) is a classical method for recovering latent variables with useful identifiability properties. For independent variables, cumulant tensors are diagonal; relaxing independence yields tensors whose zero structure generalizes diagonality. These models have…
arXiv:2502.02463v2 Announce Type: replace Abstract: While Bayesian inference provides a principled framework for reasoning under uncertainty, its widespread adoption is limited by the intractability of exact posterior computation, necessitating the use of approximate inference. However, existing methods are often computationally…
arXiv:2510.07589v1 Announce Type: cross Abstract: Understanding molecular structure, dynamics, and reactivity requires bridging processes that occur across widely separated time scales. Conventional molecular dynamics simulations provide atomistic resolution, but their femtosecond time steps limit access to the slow conformational changes…
arXiv:2510.07732v1 Announce Type: cross Abstract: We propose to perform mean-field variational inference (MFVI) in a rotated coordinate system that reduces correlations between variables. The rotation is determined by principal component analysis (PCA) of a cross-covariance matrix involving the target’s score…
arXiv:2505.16051v2 Announce Type: replace Abstract: Predicting potential and counterfactual outcomes from observational data is central to clinical decision-making, where physicians must weigh treatments for an individual patient rather than relying solely on average effects at the population level. We propose…
arXiv:2510.07904v1 Announce Type: cross Abstract: Engineering design involves demanding models encompassing many decision variables and uncontrollable parameters. In addition, unavoidable aleatoric and epistemic uncertainties can be very impactful and add further complexity. The state-of-the-art adopts two steps, uncertainty quantification and…
arXiv:2510.07935v1 Announce Type: cross Abstract: This paper presents four theoretical contributions that improve the usability of risk certificates for neural networks based on PAC-Bayes bounds. First, two bounds on the KL divergence between Bernoulli distributions enable the derivation of the…
arXiv:2206.03234v4 Announce Type: replace-cross Abstract: We propose methods for auditing multiclass classifiers for fairness under multiclass equalized odds,by estimating the deviation from equalized odds when the classifier is not completely fair. We generalize to multiclass classifiers the measure of Disparate…
