arXiv:2606. 02345v1 Announce Type: cross Abstract: Many machine learning problems, including similarity learning, ranking, and clustering, rely on empirical pairwise loss functions whose quadratic computational cost quickly becomes prohibitive at scale.
arXiv:2606. 12913v2 Announce Type: replace Abstract: The rapid growth of modern training datasets has significantly increased computational cost, motivating dataset pruning~(DP) methods which retain only a subset of informative samples to reduce training cost.
arXiv:2606. 04451v1 Announce Type: new Abstract: Neighbor embedding algorithms reveal correlations in high-dimensional data by constructing an equivalent graph representation in a lower-dimensional space.
The paper introduces a scalable subgraph sampling method that uses resistance curvature to guide the selection of nodes and edges for graph neural network training. It builds on ERC‑LG, a curvature approximation technique that employs Johnson‑Lindenstrauss projections and regularized multi‑GPU batched conjugate gradient solvers, thereby avoiding costly Laplacian pseudoinverse calculations and large embedding storage. Experiments demonstrate that ERC‑LG‑based sampling matches pseudoinverse‑based curvature numerically, runs faster than conjugate‑gradient‑only approaches, and achieves the best mean accuracy on six of seven real‑world node‑classification datasets.
arXiv:2506. 22427v2 Announce Type: replace-cross Abstract: We propose CLoVE (Clustering of Loss Vector Embeddings), a novel algorithm for Clustered Federated Learning (CFL).
arXiv:2608. 10045v1 Announce Type: cross Abstract: The problem of learning from pairwise comparisons has been widely studied across many domains such as recommendation systems, social choice, and more recently, fine-tuning large language models.
The paper introduces Backward Kernel Herding, an algorithm that iteratively removes data points to create representative subsets for kernel learning, achieving performance comparable to state‑of‑the‑art methods while speeding up subsampling when the reduced size is less than half the original dataset. It also proposes Flexible Kernel Thinning, an extension that allows construction of subsets of any size, not just successive halvings, and demonstrates that this method often yields the best predictive performance. Experiments on Gaussian Processes and Kernel Support Vector Machines show that Backward Kernel Herding excels in training‑time efficiency, while Flexible Kernel Thinning offers superior predictive accuracy and competitive memory usage, emphasizing the need to choose a reduction strategy based on the desired trade‑off between performance, cost, and memory.
arXiv:2410. 02628v5 Announce Type: replace Abstract: Learning conditional distributions $\pi^*(\cdot|x)$ is a central problem in machine learning, which is typically approached via supervised methods with paired data $(x,y) \sim \pi^*$.
arXiv:2606. 27171v1 Announce Type: new Abstract: This work addresses the problem of variance in stochastic gradient estimation for machine learning optimization.
arXiv:2607. 12916v1 Announce Type: new Abstract: In this work, we introduce CoCo, a loss function aimed at learning normalized and well-structured representations.
The paper investigates which data sources should be jointly learned when training shared feature extractors. Focusing on a linear setting where sources share a low‑dimensional subspace, it shows that carefully selecting a subset of sources—an informative subpopulation—can achieve minimax optimal subspace estimation, even when much data is discarded. The authors formalize this notion, propose algorithms and heuristics for identifying such subsets, and validate their effectiveness through theory and experiments on synthetic and real datasets.
arXiv:2607. 20367v1 Announce Type: new Abstract: Correlation alignment and the maximum mean discrepancy are two widely used distribution-matching frameworks for unsupervised domain adaptation (UDA).
arXiv:2602. 17894v2 Announce Type: replace-cross Abstract: Data collection is a critical component of modern statistical and machine learning pipelines, particularly when data must be gathered from multiple heterogeneous sources to study a target population of interest.