technocracy

arXiv:2412.19436v2 Announce Type: replace Abstract: Reinforcement learning from human feedback (RLHF) has become a cornerstone for aligning large language models with human preferences. However, the heterogeneity of human feedback, driven by diverse individual contexts and preferences, poses significant challenges for reward learning. To address this, we propose a Low-rank Contextual RLHF (LoCo-RLHF) framework that integrates contextual information to better model heterogeneous feedback while maintaining computational efficiency. Our approach builds on a contextual preference model, leveraging the intrinsic low-rank […]

Ver mais

arXiv:2602.13442v1 Announce Type: cross Abstract: Quantifying the complexity of feed-forward neural networks (FFNNs) remains challenging due to their nonlinear, hierarchical structure and numerous parameters. We apply generalized degrees of freedom (GDF) to measure model complexity in FFNNs with binary outcomes, adapting the algorithm for discrete responses. We compare GDF with both the effective number of parameters derived via log-likelihood cross-validation and the null degrees of freedom of Landsittel et al. Through simulation studies and a real data analysis, […]

Ver mais

arXiv:2512.16383v2 Announce Type: replace-cross Abstract: Quantifying predictive uncertainty is essential for safe and trustworthy real-world AI deployment. Yet, fully nonparametric estimation of conditional distributions remains challenging for multivariate targets. We propose Tomographic Quantile Forests (TQF), a nonparametric, uncertainty-aware, tree-based regression model for multivariate targets. TQF learns conditional quantiles of directional projections $mathbf{n}^{top}mathbf{y}$ as functions of the input $mathbf{x}$ and the unit direction $mathbf{n}$. At inference, it aggregates quantiles across many directions and reconstructs the multivariate conditional distribution by […]

Ver mais

arXiv:2601.20981v1 Announce Type: new Abstract: Evolutionary prompt search is a practical black-box approach for red teaming large language models (LLMs), but existing methods often collapse onto a small family of high-performing prompts, limiting coverage of distinct failure modes. We present a speciated quality-diversity (QD) extension of ToxSearch that maintains multiple high-toxicity prompt niches in parallel rather than optimizing a single best prompt. ToxSearch-S introduces unsupervised prompt speciation via a search methodology that maintains capacity-limited species with exemplar leaders, […]

Ver mais

Integrating hard constraints into deep learning is essential for safety-critical systems. Yet existing constructive layers that project predictions onto constraint boundaries face a fundamental bottleneck: gradient saturation. By collapsing exterior points onto lower-dimensional surfaces, standard orthogonal projections induce rank-deficient Jacobians, which nullify gradients orthogonal to active constraints and hinder optimization. We introduce Soft-Radial Projection, a differentiable reparameterization layer that circumvents this issue through a radial mapping from Euclidean space into the interior of the feasible set. This construction […]

Ver mais

arXiv:2605.04269v1 Announce Type: new Abstract: We provide a theoretical analysis of Adam under non-stationary stochastic objectives, separating two regimes: Euclidean tracking under adaptive strong monotonicity of the Adam-preconditioned mean-gradient operator, and high-probability projected stationarity guarantees under general $L$-smooth objectives. In the tracking regime, we derive finite-time expected and high-probability bounds that decompose sharply into four components: initialization, objective drift, a first-moment tracking error governed by $beta_1$, and a preconditioner perturbation governed by $beta_2$. We characterize the burn-in time […]

Ver mais

arXiv:2605.11059v1 Announce Type: new Abstract: We study the large-depth limit of transformers trained with AdamW, by modelling the hidden-state dynamics as an interacting particle system (IPS) coupled through the attention mechanism. Under appropriate scaling of the attention heads, we prove that the joint dynamics of the hidden states and backpropagated variables converge in $L^2$, uniformly over the initial condition, to the solution of a forward–backward system of ODEs at rate $mathcal O(L^{-1}+L^{-1/3}H^{-1/2})$. Here, $L$ and $H$ denote the […]

Ver mais

arXiv:2603.10027v1 Announce Type: new Abstract: Empiric antibiotic prescribing in high-risk clinical contexts often requires decision making under conditions of incomplete information, where inappropriate coverage or unjustified escalation may compromise safety and antimicrobial stewardship. While clinical decision-support systems have been proposed to assist in this process, many approaches lack explicit governance and evaluation mechanisms defining scope, abstention conditions, recommendation permissibility, and expected system behavior. This work specifies a governance and evaluation framework for deterministic clinical decision-support systems operating under […]

Ver mais