January 2026

arXiv:2510.21974v2 Announce Type: replace-cross Abstract: We introduce Deep Jump Gaussian Processes (DJGP), a novel method for surrogate modeling of a piecewise continuous function on a high-dimensional domain. DJGP addresses the limitations of conventional Jump Gaussian Processes (JGP) in high-dimensional input spaces by integrating region-specific, locally linear projections with JGP modeling. These projections employ region-dependent matrices to capture local low-dimensional subspace structures, making them well suited to the inherently localized modeling behavior of JGPs, a variant of local Gaussian […]

Ver mais

arXiv:2509.16180v2 Announce Type: replace-cross Abstract: We propose an algorithm with improved query-complexity for the problem of hypothesis selection under local differential privacy constraints. Given a set of $k$ probability distributions $Q$, we describe an algorithm that satisfies local differential privacy, performs $tilde{O}(k^{3/2})$ non-adaptive queries to individuals who each have samples from a probability distribution $p$, and outputs a probability distribution from the set $Q$ which is nearly the closest to $p$. Previous algorithms required either $Omega(k^2)$ queries or […]

Ver mais

arXiv:2504.01807v3 Announce Type: replace-cross Abstract: Certifying safety in dynamical systems is crucial, but barrier certificates – widely used to verify that system trajectories remain within a safe region – typically require explicit system models. When dynamics are unknown, data-driven methods can be used instead, yet obtaining a valid certificate requires rigorous uncertainty quantification. For this purpose, existing methods usually rely on full-state measurements, limiting their applicability. This paper proposes a novel approach for synthesizing barrier certificates for unknown […]

Ver mais

arXiv:2502.17772v4 Announce Type: replace-cross Abstract: Differentially Private Stochastic Gradient Descent (DPSGD) is widely used to protect sensitive data during the training of machine learning models, but its privacy guarantee often comes at a large cost of model performance due to the lack of tight theoretical bounds quantifying privacy loss. While recent efforts have achieved more accurate privacy guarantees, they still impose some assumptions prohibited from practical applications, such as convexity and complex parameter requirements, and rarely investigate in-depth […]

Ver mais

arXiv:2502.10510v3 Announce Type: replace-cross Abstract: Modern machine learning pipelines are increasingly combining and mixing data from diverse and disparate sources, e.g., pre-training large language models. Yet, finding the optimal data mixture is a challenging and open problem. We formalize this data mixing problem as a bi-level objective: the best mixture is the one that would lead to the best model for a downstream objective. Unfortunately, this objective is generally intractable. In this paper, we make the observation that […]

Ver mais

arXiv:2410.21105v2 Announce Type: replace-cross Abstract: We propose a difference-in-differences (DiD) framework designed for time-varying continuous treatments across multiple periods. Specifically, we estimate the average treatment effect on the treated (ATET) by comparing distinct non-zero treatment intensities. Identification rests on a conditional parallel trends assumption that accounts for observed covariates and past treatment histories. Our approach allows for lagged treatment effects and, in repeated cross-sectional settings, accommodates compositional changes in covariates. We develop kernel-based ATET estimators for both repeated […]

Ver mais

arXiv:2306.01468v3 Announce Type: replace-cross Abstract: Measurement error occurs when a covariate influencing a response variable is corrupted by noise. This can lead to misleading inference outcomes, particularly in problems where accurately estimating the relationship between covariates and response variables is crucial, such as causal effect estimation. Existing methods for dealing with measurement error often rely on strong assumptions such as knowledge of the error distribution or its variance and availability of replicated measurements of the covariates. We propose […]

Ver mais

arXiv:2511.23310v2 Announce Type: replace Abstract: Existing reinforcement learning (RL)-based post-training methods for large language models have advanced rapidly, yet their design has largely been guided by heuristics rather than systematic theoretical principles. This gap limits our understanding of the properties of the gradient estimators and the associated optimization algorithms, thereby constraining opportunities to improve training stability and overall performance. In this work, we provide a unified theoretical framework that characterizes the statistical properties of commonly used policy-gradient estimators […]

Ver mais

arXiv:2510.04277v2 Announce Type: replace Abstract: The sample complexity of estimating or maximising an unknown function in a reproducing kernel Hilbert space is known to be linked to both the effective dimension and the information gain associated with the kernel. While the information gain has an attractive information-theoretic interpretation, the effective dimension typically results in better rates. We introduce a new quantity called the relative information gain, which measures the sensitivity of the information gain with respect to the […]

Ver mais

arXiv:2509.18349v3 Announce Type: replace Abstract: Meta-learning aims to leverage information across related tasks to improve prediction on unlabeled data for new tasks when only a small number of labeled observations are available (“few-shot” learning). Increased task diversity is often believed to enhance meta-learning by providing richer information across tasks. However, recent work by Kumar et al. (2022) shows that increasing task diversity, quantified through the overall geometric spread of task representations, can in fact degrade meta-learning prediction performance […]

Ver mais