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.

This paper introduces a novel, efficient protocol for training Gradient Boosting Decision Trees (GBDT) on vertically partitioned data held by two mutually distrustful parties while ensuring complete a…

This paper compares traditional machine learning models (Random Forests, XGBoost, SVM) against a complex Unified Multi-Task Time Series Model for churn prediction, concluding that conventional methods…

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 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 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…

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 proposes pretraining a Perceiver-style in-context learner on synthetic data to solve Multiple Instance Learning (MIL) tasks efficiently in the low-label regime.

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…

This paper addresses the challenge of achieving optimal fairness and accuracy simultaneously in multi-class classification by proposing novel in-processing and post-processing algorithms that converge…

The paper introduces ProbMoE, a probabilistic routing framework that tackles the non-differentiability of top-$k$ routing in Mixture-of-Experts (MoE) models, achieving strong performance with improved…

SUPREME is an open-source, multi-GPU framework designed to efficiently and reproducibly evaluate machine unlearning methods for image classification by distributing computationally intensive tasks acr…

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 introduces a method to automatically determine the optimal learning period ($ au$) for the Random Gradient hyper-heuristic, enabling it to optimally solve Pseudo-Boolean Problems without ma…

The paper proposes a robust, multi-stage pipeline combining rule-based classification and machine learning to map noisy retail product names to standardized consumption categories, finding that simple…

TailLoR is a new parameter-efficient finetuning method that uses the singular bases of pre-trained weights to learn low-rank updates, specifically penalizing updates along dominant directions to impro…

The paper investigates applying Riemannian optimization techniques to low-rank matrix parameters for deep learning, but finds that the proposed methods do not conclusively outperform the AdamW baselin…

The paper introduces Drifting Preference Optimization (DrPO), an efficient online method for preference finetuning one-step text-to-image generators that avoids complex gradient calculations and model…

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.