The paper investigates the difference between cost‑agnostic and cost‑sensitive loss functions when model capacity is limited. It shows that, unlike in ideal infinite‑capacity settings, optimizing a cost‑sensitive objective can yield a strictly better downstream decision than post‑processing a cost‑agnostic model. The authors prove this gap under a hypothesis class that can recover the optimal decision boundary but not the optimal cost‑agnostic hypothesis, and provide a simple example and empirical evidence on UCI datasets with simple models.
arXiv:2607. 10694v1 Announce Type: cross Abstract: We study the problem of optimal continual fine-tuning for a pre-trained Foundation Model deployed at a resource-limited device.
The paper investigates the consistency of surrogate loss methods for classification and policy learning when the set of admissible classifiers is constrained, such as by interpretability or fairness requirements. It shows that hinge loss is the only surrogate that preserves consistency when constraints limit only the prediction set, but consistency can fail if constraints also restrict the functional form. The authors derive conditions guaranteeing consistency for hinge-risk-minimizing classifiers and use these results to design efficient hinge-loss-based procedures for monotone classification problems.
arXiv:2603. 06957v2 Announce Type: replace-cross Abstract: We study post-training linear autoregressive models with outcome and process rewards.
arXiv:2509. 22992v2 Announce Type: replace Abstract: As machine learning models continue to grow in size and complexity, efficient serving faces increasingly broad trade-offs spanning accuracy, latency, resource usage, and other objectives.
The paper introduces a new approach to safety in contextual bandits with continuous actions, focusing on high‑probability constraints on the realized cost rather than expected cost. It presents the High‑Probability Constrained UCB algorithm, which balances reward exploration with conservative safety estimation, and provides theoretical regret guarantees for linear models and extensions to general function classes. Experiments demonstrate that this realized‑cost safety framework significantly reduces safety violations compared to expected‑cost constrained methods.
arXiv:2606. 01081v1 Announce Type: new Abstract: Decision-focused learning (DFL) trains predictive models by optimizing downstream decision quality rather than standalone prediction accuracy.
arXiv:2604. 27742v2 Announce Type: replace Abstract: A fundamental dichotomy in the theory of classification sets smoothness against statistical efficiency: smooth surrogate losses such as the logistic loss enable fast $O(1/T)$ optimization but yield slow square-root $H$-consistency bounds, while piecewise-linear losses like the Hinge loss achieve optimal linear $H$-consistency rates but are non-differentiable.
The paper presents a new scaling law for reward optimization in AI alignment, showing that performance scales as Θ(√min{log(M), K}), where M is the number of preference comparisons used to train a proxy reward model and K is the KL‑divergence budget relative to a reference policy. The authors derive this law using an information‑theoretic model, prove its tightness, and validate it with extensive experiments involving a 70B gold reward model and smaller proxy models (0.6B–4B). The empirical results demonstrate a strong fit (R² 97–99 %) across different model sizes, noise levels, and optimization methods, suggesting that reward optimization behaves like a simple selection task over IID Gaussian variables with noisy feedback.
arXiv:2607. 26577v1 Announce Type: new Abstract: Adaptive conformal inference (ACI) of Gibbs and Cand{\`e}s and its variants are the standard approach to online conformal prediction under distribution shift, but they suffer from three fundamental limitations.
The paper introduces a new approach to safety in contextual bandits with continuous actions by enforcing high‑probability constraints on the realized cost rather than on its expectation. It proposes the High‑Probability Constrained UCB algorithm, which balances optimistic reward exploration with pessimistic safety estimation. The authors provide theoretical regret guarantees for linear models and extend the analysis to general function classes, demonstrating experimentally that realized‑cost constraints significantly reduce safety violations compared to expected‑cost baselines.
arXiv:2606. 19587v1 Announce Type: cross Abstract: We propose a scalable method for training prediction (machine learning) models in the predict-then-optimize paradigm, where model outputs serve as coefficients for a subsequent linear optimization task.
arXiv:2606. 01527v2 Announce Type: replace Abstract: Machine unlearning is motivated by legal and user-facing requirements to remove the influence of individuals' data from trained models, such as the right to be forgotten.