March 2026

eeking arXiv cs.LG endorsement for a paper on activation probe transfer failure for reward hacking detection. I test whether probes trained on the School of Reward Hacks dataset (Taylor et al. 2025) transfer to GRPO-induced reward seeking. They don’t. The SFT and RL probe directions are nearly orthogonal (cosine = -0.07). Paper builds on Wilhelm et al. 2026, Taufeeque et al. 2026, and Gupta & Jenner 2025 (NeurIPS MechInterp Workshop). Paper will be visible on arXiv once endorsed […]

Ver mais

arXiv:2603.20655v2 Announce Type: replace-cross Abstract: We introduce Exponential Family Discriminant Analysis (EFDA), a unified generative framework that extends classical Linear Discriminant Analysis (LDA) beyond the Gaussian setting to any member of the exponential family. Under the assumption that each class-conditional density belongs to a common exponential family, EFDA derives closed-form maximum-likelihood estimators for all natural parameters and yields a decision rule that is linear in the sufficient statistic, recovering LDA as a special case and capturing nonlinear decision […]

Ver mais

arXiv:2601.13698v2 Announce Type: replace-cross Abstract: Fairness and privacy are two vital pillars of trustworthy machine learning. Despite extensive research on these individual topics, their relationship has received significantly less attention. In this paper, we utilize an information-theoretic measure Chernoff Information to characterize the fundamental trade-off between fairness, privacy, and accuracy, as induced by the input data distribution. We first propose Chernoff Difference, a notion of data fairness, along with its noisy variant, Noisy Chernoff Difference, which allows us […]

Ver mais

arXiv:2512.04165v4 Announce Type: replace-cross Abstract: Two pressing topics in the theory of deep learning are the interpretation of feature learning (FL) mechanisms and the determination of implicit bias of networks in the rich regime. Current theories of rich FL often appear in the form of high-dimensional non-linear equations, which require computationally intensive numerical solutions. Given the many details that go into defining a deep learning problem, this analytical complexity is a significant and often unavoidable challenge. Here, we […]

Ver mais

arXiv:2510.27211v5 Announce Type: replace-cross Abstract: It is known that the minimum-mean-squared-error (MMSE) denoiser under Gaussian noise can be written as a proximal operator, which suffices for asymptotic convergence of plug-and-play (PnP) methods but does not reveal the structure of the induced regularizer or give convergence rates. We show that the MMSE denoiser corresponds to a regularizer that can be written explicitly as an upper Moreau envelope of the negative log-marginal density, which in turn implies that the regularizer […]

Ver mais

arXiv:2510.08294v2 Announce Type: replace-cross Abstract: We address the open question of counterfactual identification for high-dimensional multivariate outcomes from observational data. Pearl (2000) argues that counterfactuals must be identifiable (i.e., recoverable from the observed data distribution) to justify causal claims. A recent line of work on counterfactual inference shows promising results but lacks identification, undermining the causal validity of its estimates. To address this, we establish a foundation for multivariate counterfactual identification using continuous-time flows, including non-Markovian settings under […]

Ver mais

arXiv:2510.03131v3 Announce Type: replace-cross Abstract: Modern regression analyses are often undermined by covariate measurement error, misspecification of the regression model, and misspecification of the measurement error distribution. We present, to the best of our knowledge, the first Bayesian nonparametric learning framework targeting total robustness to all three challenges in general nonlinear regression. Our framework places a joint Dirichlet process prior on the latent covariate–response distribution and updates it with posterior pseudo-samples of the latent covariates, so that inference […]

Ver mais