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

This paper proposes a preconditioning layer for stable weight conditioning in LLM training.

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…

A new boosting algorithm that strong learns concept classes closed under O(log 1/γ)-XOR using O(log 1/ε) calls to a γ-advantage weak learner and additional samples, by connecting boosting with list-de…

This paper extends gradient boosting to functions of vector inputs using a simple algorithm with histogram-based decision trees.

This paper proposes using offline reinforcement learning (RL) as an efficient alternative to online RL for post-training code-generating LLMs, demonstrating its effectiveness, especially for smaller m…

This book provides a compact, derivation-oriented mathematical primer that connects major families of generative AI models, showing their underlying structural relationships.

This paper presents a memory-efficient training stack for Mixture-of-Experts (MoE) models, combining and specializing parallelism techniques for maximal efficiency.

The paper demonstrates the potential of using LLMs within verifier-guided evolutionary coding agents to develop and improve algorithms, specifically applied to contraction order optimization in tensor…

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 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 proposes a data collection strategy using solver iterates to augment datasets for training generative models, improving the efficiency of the data-model-optimization loop in one-sided box-c…

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…

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…

This paper demonstrates that adversarial perturbations possess a low-rank structure, and proposes a two-step method to leverage this property to significantly improve the efficiency and effectiveness…

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 introduces Sparse Memory-Efficient Training (SMET), a method that stabilizes and optimizes Dynamic Sparse Training (DST) for large language models, enabling stable and memory-efficient spars…

The paper proposes $D^3$, a dynamic graph-constrained scheduling framework that optimizes LLM training order by modeling sample interactions as a dynamic influence graph.