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 introduces Inconsistency-Aware Minimization (IAM), a novel training objective that uses a label-free measure called local inconsistency to improve model generalization, particularly in semi-…

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 a novel, practical upper bound to estimate the worst-case performance of medical prediction models on the target population, even when the selection bias mechanism and target data a…

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…

This paper proposes DeMix, a novel framework for simultaneously diagnosing erroneous samples and their error types in machine learning models.

The study assesses the generalization capability of supervised machine learning models for intrusion detection using UNSW-NB15 and TON_IoT, finding a significant performance drop when models are teste…

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 introduces polynomial representations as a quantitative, distribution-aware metric for measuring model simplicity, demonstrating that the effective degree of this representation is a superio…

The paper challenges the conclusion that LLMs lack reasoning by demonstrating that reported performance drops on GSM-Symbolic are often statistically weak and partially attributable to dataset biases,…

The paper introduces LearnWeak, an annotation-free framework that automatically specializes small computer-use agents by identifying and targeting their specific weaknesses using a stronger reference…

The paper proposes a new, optimal estimator for semiparametric inference that improves upon standard double machine learning (DML) rates by eliminating the first-order stochastic error of nuisance fun…

The paper introduces trust functions to filter weak supervision labels, enabling near-lossless weak-to-strong generalization by selectively training a strong student using only the most reliable weak…

The paper proposes SubFit, a novel compression technique that achieves superior LLM compression by replacing non-contiguous, submodule-level components (Attention and FeedForward) with lightweight res…

The paper proposes a novel layer and point-wise projection mapping combined with LoRA injection to efficiently distill knowledge from a large teacher model to a small student model, significantly impr…

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…

This paper systematically studies how soft errors propagate during Large Language Model (LLM) inference using a novel fault-injection framework, providing critical insights and mitigation strategies f…

The paper introduces SORA, an adaptive adversarial training method that dynamically adjusts perturbation sizes to prevent Catastrophic Overfitting, achieving state-of-the-art robustness and clean accu…

LiteGuard proposes an efficient task-agnostic model fingerprinting framework that achieves enhanced generalization and significantly reduces computational overhead compared to existing methods like Me…