February 2026

arXiv:2407.21082v2 Announce Type: replace-cross Abstract: This paper presents a modular approach to accelerate inference in large language models (LLMs) by adding early exit heads at intermediate transformer layers. Each head is trained in a self-supervised manner to mimic the main model’s predictions, allowing computation to stop early when a calibrated confidence threshold is reached. We evaluate several confidence metrics and show that entropy provides the most reliable separation between correct and incorrect predictions. Experiments on the Pythia model […]

Ver mais

arXiv:2403.20200v4 Announce Type: replace-cross Abstract: High-dimensional linear regression has been thoroughly studied in the context of independent and identically distributed data. We propose to investigate high-dimensional regression models for independent but non-identically distributed data. To this end, we suppose that the set of observed predictors (or features) is a random matrix with a variance profile and with dimensions growing at a proportional rate. Assuming a random effect model, we study the predictive risk of the ridge estimator for […]

Ver mais

arXiv:2204.06990v4 Announce Type: replace-cross Abstract: We consider observations $(X,y)$ from single index models with unknown link function, Gaussian covariates and a regularized M-estimator $hatbeta$ constructed from convex loss function and regularizer. In the regime where sample size $n$ and dimension $p$ are both increasing such that $p/n$ has a finite limit, the behavior of the empirical distribution of $hatbeta$ and the predicted values $Xhatbeta$ has been previously characterized in a number of models: The empirical distributions are known […]

Ver mais

arXiv:2601.20269v2 Announce Type: replace Abstract: Machine learning models in high-stakes applications, such as recidivism prediction and automated personnel selection, often exhibit systematic performance disparities across sensitive subpopulations, raising critical concerns regarding algorithmic bias. Fairness auditing addresses these risks through two primary functions: certification, which verifies adherence to fairness constraints; and flagging, which isolates specific demographic groups experiencing disparate treatment. However, existing auditing techniques are frequently limited by restrictive distributional assumptions or prohibitive computational overhead. We propose a novel […]

Ver mais

arXiv:2601.16250v2 Announce Type: replace Abstract: We study a general framework of distributional computational graphs: computational graphs whose inputs are probability distributions rather than point values. We analyze the discretization error that arises when these graphs are evaluated using finite approximations of continuous probability distributions. Such an approximation might be the result of representing a continuous real-valued distribution using a discrete representation or from constructing an empirical distribution from samples (or might be the output of another distributional computational […]

Ver mais

arXiv:2601.13458v2 Announce Type: replace Abstract: The increasing reliance on human preference feedback to judge AI-generated pseudo labels has created a pressing need for principled, budget-conscious data acquisition strategies. We address the crucial question of how to optimally allocate a fixed annotation budget between ground-truth labels and pairwise preferences in AI. Our solution, grounded in semi-parametric inference, casts the budget allocation problem as a monotone missing data framework. Building on this formulation, we introduce Preference-Calibrated Active Learning (PCAL), a […]

Ver mais

arXiv:2510.24187v2 Announce Type: replace Abstract: We consider the adversarial linear bandits setting and present a unified algorithmic framework that bridges Follow-the-Regularized-Leader (FTRL) and Follow-the-Perturbed-Leader (FTPL) methods, extending the known connection between them from the full-information setting. Within this framework, we introduce self-concordant perturbations, a family of probability distributions that mirror the role of self-concordant barriers previously employed in the FTRL-based SCRiBLe algorithm. Using this idea, we design a novel FTPL-based algorithm that combines self-concordant regularization with efficient stochastic […]

Ver mais

arXiv:2509.22341v2 Announce Type: replace Abstract: Model collapse occurs when generative models degrade after repeatedly training on their own synthetic outputs. We study this effect in overparameterized linear regression in a setting where each iteration mixes fresh real labels with synthetic labels drawn from the model fitted in the previous iteration. We derive precise generalization error formulae for minimum-$ell_2$-norm interpolation and ridge regression under this iterative scheme. Our analysis reveals intriguing properties of the optimal mixing weight that minimizes […]

Ver mais

arXiv:2505.13732v5 Announce Type: replace Abstract: We introduce $textit{Backward Conformal Prediction}$, a method that guarantees conformal coverage while providing flexible control over the size of prediction sets. Unlike standard conformal prediction, which fixes the coverage level and allows the conformal set size to vary, our approach defines a rule that constrains how prediction set sizes behave based on the observed data, and adapts the coverage level accordingly. Our method builds on two key foundations: (i) recent results by Gauthier […]

Ver mais

arXiv:2602.12107v1 Announce Type: cross Abstract: We study offline reinforcement learning under $Q^star$-approximation and partial coverage, a setting that motivates practical algorithms such as Conservative $Q$-Learning (CQL; Kumar et al., 2020) but has received limited theoretical attention. Our work is inspired by the following open question: “Are $Q^star$-realizability and Bellman completeness sufficient for sample-efficient offline RL under partial coverage?” We answer in the negative by establishing an information-theoretic lower bound. Going substantially beyond this, we introduce a general framework […]

Ver mais