This paper establishes a large deviation principle for the generalization error of interpolating classifiers in the overparametrized regime.

This paper investigates limitations of learning tanh neural networks under finite-precision computations and Lp accuracy guarantees.

The paper proposes WEINCE, a modified InfoNCE objective that uses extreme value theory corrections to improve contrastive learning by more accurately modeling the selection of hard negative examples.

This paper proposes Tail-Aware Adaptive-k (TAA-k), a training-free framework for adaptive context selection in retrieval-augmented generation systems using Extreme Value Theory.

This paper improves the theoretical bounds for estimating discrete probability distributions using the $\ell_\infty$ norm, resolving several open questions in the field.

This paper introduces and analyzes a consistent estimator for the sub-Gaussian parameter ($\xi_*^2$), providing convergence rates and demonstrating its applicability in large-scale biological enrichme…

This paper shows that standard optimal control in Markov Decision Processes (MDPs) with an absorbing catastrophic state naturally generates behavioral signatures mimicking prospect theory, even withou…

This paper proposes a reliability-aware framework to solve the fuzzy shortest path problem in directed graphs, optimizing routes based not only on cost but also on the reliability of the associated fu…

This paper develops a novel, computationally efficient method to quantify the uncertainty in wide neural network predictions by characterizing the limiting random fluctuations using stochastic evoluti…

The paper analyzes preference-shaped expected improvement criteria for Bayesian multiobjective optimization, precisely characterizing when transformations preserve key properties like exact computatio…

The paper analyzes the potential market impact of a large, unknown Bitcoin holder (the Satoshi overhang) and concludes that the mechanical downside risk is bounded, suggesting the terminal states are…

The paper introduces MINTS, a minimalist Bayesian framework that simplifies sequential decision-making by placing priors only on the optimum location, allowing for the incorporation of structural cons…

The paper analyzes robust covert wireless communication under bounded uncertainty, demonstrating that the adverse conditions governing reliability and covertness are distinct, thus requiring a conflic…

The paper analyzes the phase transitions of the noisy transformer model on the unit sphere, proving a sharp global-minimizer dichotomy that depends on the dimension and coupling strength.

E4GEN introduces an explainable diffusion framework that significantly improves time-series generation by specifically focusing on and controlling the fidelity of extreme events.

The paper provides a formal proof that a single C program can contain a countably infinite number of distinct, independently assignable software vulnerabilities, suggesting the set of all software vul…

The paper introduces and analyzes several novel data appraisal metrics, including the Vendi Score and matrix spectral functions, demonstrating that efficient optimization techniques make these metrics…

The paper introduces the linear canonical Riesz potential (LCRP) and analyzes its convergence properties, leveraging these findings to propose a novel, secure, and efficient asymmetric cascaded LCRP m…

The paper characterizes the optimal achievable rate for differentially private hypothesis testing using e-values, providing an exact algorithm for both fixed and sequential settings.

The paper improves Banaszczyk's inequality, providing a significantly better tail estimate for the discrete Gaussian measure on a lattice, which has applications in analyzing dual attacks against the…