← Back to all news
arXiv Machine Learning By Walid Bendada, Guillaume Salha-Galvan

Two-Level Softmax Sampling Done Right: Correcting Bias from Size Imbalance and Dispersion

Read the original on arXiv Machine Learning →

The paper addresses the bias introduced by two‑level softmax (2LS) sampling, which partitions items into clusters and samples a cluster before an item. It identifies that 2LS misweights clusters by ignoring size imbalance and intra‑cluster similarity dispersion, leading to systematic sampling bias. The authors propose two corrected methods, Size‑Corrected 2LS (S‑2LS) and Size‑ and Dispersion‑Corrected 2LS (SD‑2LS), that eliminate these biases with negligible computational overhead and demonstrate improved sampling performance on five large‑scale datasets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Oct 7

Fed-BRDECS: Privacy-Preserving and Heterogeneity-Aware Federated Deep Embedded Clustering

Fed-BRDECS is a federated deep embedded clustering framework that protects client privacy by replacing globally normalized clustering objectives with a locally computable sample‑stability loss, eliminating the need to share sensitive soft‑assignment distributions. It addresses non‑IID client data through prediction‑balanced sampling, which oversamples rare predicted clusters, and centroid‑level restarting, which refreshes biased or inactive centroids. Experiments on image, text, and time‑series datasets demonstrate that Fed‑BRDECS outperforms existing federated and deep clustering methods while adding no inference‑time cost for anomaly detection.

By Haemin Park, Diego Klabjan, Martin W. Braun, Xiuqi Li, Balakrishnan Ananthanarayanan
benchmarkssafety
More like this →