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

This paper develops statistical learning theory for gradient boosting in Peaks-over-Threshold modeling using Generalized Pareto distributions, deriving error bounds and reducing gradient correlation.

The paper proposes a novel structural invariant approach, derived from the economic constraints of fraud, that amplifies weak, low-precision signals into highly accurate fraud detections without requi…

The paper introduces PRAXIS, a novel algorithm that efficiently approximates the computation of 'Rashomon sets' for decision trees, significantly reducing memory and runtime complexity.

The paper analyzes the sample complexity of contextual bandits in the $s$-sparse setting, achieving optimal sample bounds for identifying an $\epsilon$-optimal policy.

The paper formalizes the problem of representation identifiability in supervised learning, showing that a representation property is identifiable if and only if it is constant across all possible fact…

The paper introduces Score Broadcast and Decorrelation (SBD), a general theoretical framework that unifies broadcast-based credit assignment across various differentiable loss functions by leveraging…

The paper analyzes a new class of asynchronous adaptive first-order optimization methods and proves their stochastic convergence rate is O(1/sqrt{t}) for non-convex functions.

This paper provides the first non-vacuous generalization analysis for the Stochastic Variance Reduced Gradient (SVRG) method by establishing sharp, data-dependent algorithmic stability bounds, thereby…

The paper proposes DiReCT, a novel framework that treats data selection during LLM annealing as a constrained optimization problem based on the spectral geometry of the loss landscape, achieving state…

This paper introduces survey sampling techniques to estimate or minimize empirical pairwise loss functions, showing that targeting informative pairs significantly reduces computational cost while main…

The paper establishes the first theoretical framework for analyzing the learnability of Test-Time Adaptation (TTA) under non-stationary data streams by introducing Recovery Complexity, which quantifie…

The paper establishes tight upper and lower bounds on the statistical cost of approximate machine unlearning for smooth strongly convex losses, showing that the optimal unlearning rate depends critica…

The paper introduces a new anytime-valid inference method to correct split selection in online decision trees, providing robust statistical guarantees for streaming data that existing methods lack.

This paper measures the lower bound for the shortest program generating a sequence, proving a conservation law and providing a deterministic engine to recover generating programs for certain sequences…

This paper analyzes the poor performance of Meta-learning for Training-data Selection (MTS) and proposes that increasing the batch size and incorporating informative features can significantly improve…

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…

The paper proposes DAMEL, a dual-axis multi-expert learning algorithm that simultaneously reduces both prediction bias and variance in class-imbalanced learning by leveraging multiple experts across b…

The paper presents a new worst-case to average-case reduction for the Learning Parity with Noise (LPN) problem, achieving hardness for inverse-polynomial noise rates previously unattainable.

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