paper-with-me

Papers

Submodular Batch Selection for Training Deep Neural Networks

2019-06-20 · K J Joseph, Vamshi Teja R, Krishnakant Singh, Vineeth N. Balasubramanian

Mini-batch gradient descent based methods are the de facto algorithms for training neural network architectures today. We introduce a mini-batch selection strategy based on submodular function maximization. Our novel submodular formulation captures the informativeness of each sample and diversity of the whole subset. We design an efficient, greedy algorithm which can give high-quality solutions to this NP-hard combinatorial optimization problem. Our extensive experiments on standard datasets show that the deep models trained using the proposed batch selection strategy provide better generalization than Stochastic Gradient Descent as well as a popular baseline sampling strategy across different learning rates, batch sizes, and distance metrics.

📄 PDF Abstract BibTeX arXiv:1906.08771

Code (1)

VamshiTeja/SMDL 공식 구현 pytorch

Tasks

Combinatorial OptimizationDiversityInformativeness

Similar Papers 제목 키워드 기반

Partial-Adaptive Submodular Maximization

2021-11-01 · Shaojie Tang, Jing Yuan

The goal of a typical adaptive sequential decision making problem is to design an interactive policy that selects a group of items sequentially, based on some partial observations, to maximize the expected utility. It ha…

Active LearningDecision MakingSequential Decision Making

Minibatch Selection for Language Models via Partition Matroid Constrained Gradient Matching

2026-06-06 · Prayas Agrawal, Prateek Chanda, Ishita Khatri, Ganesh Ramakrishnan 외 arxiv

Training large language models (LLMs) on heterogeneous data requires selecting minibatches that balance convergence speed with coverage across domains. Existing methods either select samples independently within each dom…

Active Learning Methods based on Statistical Leverage Scores

2018-12-06 · Cem Orhan, Oznur Tastan

In many real-world machine learning applications, unlabeled data are abundant whereas class labels are expensive and scarce. An active learner aims to obtain a model of high accuracy with as few labeled instances as poss…

Active Learning

Online Summarization via Submodular and Convex Optimization

2017-07-01 · CVPR 2017 7 · Ehsan Elhamifar, M. Clara De Paolis Kaluza

We consider the problem of subset selection in the online setting, where data arrive incrementally. Instead of storing and running subset selection on the entire dataset, we propose an incremental subset selection framew…

Video Summarization

Submodular Mini-Batch Training in Generative Moment Matching Networks

2017-07-18 · Jun Qi

This article was withdrawn because (1) it was uploaded without the co-authors' knowledge or consent, and (2) there are allegations of plagiarism.