paper-with-me

홈 › Papers

SeWA: Selective Weight Average via Probabilistic Masking

2025-02-14 · Peng Wang, Shengchao Hu, Zerui Tao, Guoxia Wang, dianhai yu, Li Shen, Quan Zheng, DaCheng Tao

Weight averaging has become a standard technique for enhancing model performance. However, methods such as Stochastic Weight Averaging (SWA) and Latest Weight Averaging (LAWA) often require manually designed procedures to sample from the training trajectory, and the results depend heavily on hyperparameter tuning. To minimize human effort, this paper proposes a simple yet efficient algorithm called Selective Weight Averaging (SeWA), which adaptively selects checkpoints during the final stages of training for averaging. Based on SeWA, we show that only a few points are needed to achieve better generalization and faster convergence. Theoretically, solving the discrete subset selection problem is inherently challenging. To address this, we transform it into a continuous probabilistic optimization framework and employ the Gumbel-Softmax estimator to learn the non-differentiable mask for each checkpoint. Further, we theoretically derive the SeWA's stability-based generalization bounds, which are sharper than that of SGD under both convex and non-convex assumptions. Finally, solid extended experiments in various domains, including behavior cloning, image classification, and text classification, further validate the effectiveness of our approach.

📄 PDF Abstract BibTeX arXiv:2502.10119

Code (0)

등록된 구현이 없습니다.

Tasks

Generalization Boundsimage-classificationImage Classificationtext-classificationText Classification

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…
Stochastic Weight Averaging Stochastic Weight Averaging is an optimization procedure that averages multiple points along the trajectory of SGD, with a cyclical or…

Similar Papers 제목 키워드 기반

Selective Masking based Self-Supervised Learning for Image Semantic Segmentation

2025-12-07 · Yuemin Wang, Ian Stavness arxiv

This paper proposes a novel self-supervised learning method for semantic segmentation using selective masking image reconstruction as the pretraining task. Our proposed method replaces the random masking augmentation use…

Self-Supervised LearningSemantic SegmentationImage Reconstruction

Sewage Pooling Test for SARS-CoV-2

2020-05-13 · Ritam Guha, Anik Sengupta, Ankan Dutta

CoVID-19 is currently one of the biggest threats to mankind. To date, it is the reason for infections of over 35 lakhs and the death of over 2 lakh human beings. We propose a procedure to detect CoVID-19 affected localit…

Masking as an Efficient Alternative to Finetuning for Pretrained Language Models

2020-04-26 · EMNLP 2020 11 · Mengjie Zhao, Tao Lin, Fei Mi, Martin Jaggi 외

We present an efficient method of utilizing pretrained language models, where we learn selective binary masks for pretrained weights in lieu of modifying them through finetuning. Extensive evaluations of masking BERT and…

ASMa: Asymmetric Spatio-temporal Masking for Skeleton Action Representation Learning

2026-02-05 · Aman Anand, Amir Eskandari, Elyas Rahsno, Farhana Zulkernine arxiv

Self-supervised learning (SSL) has shown remarkable success in skeleton-based action recognition by leveraging data augmentations to learn meaningful representations. However, existing SSL methods rely on data augmentati…

Self-Supervised LearningRepresentation LearningKnowledge DistillationAction Recognition

When Actions Disappear: Adversarial Action Removal in Self-Play Reinforcement Learning

2026-05-04 · Arahan Kujur arxiv

We study adversarial action masking in self-play reinforcement learning: an attacker selectively removes legal actions from a victim's action set. Unlike observation or action perturbations, removal eliminates decision o…

Reinforcement Learning