AutoSampling: Search for Effective Data Sampling Schedules

• URL: http://arxiv.org/abs/2105.13695v1
• Date: Fri, 28 May 2021 09:39:41 GMT
• Title: AutoSampling: Search for Effective Data Sampling Schedules
• Authors: Ming Sun, Haoxuan Dou, Baopu Li, Lei Cui, Junjie Yan, Wanli Ouyang
• Abstract summary: We propose an AutoSampling method to automatically learn sampling schedules for model training. We apply our method to a variety of image classification tasks illustrating the effectiveness of the proposed method.
• Score: 118.20014773014671
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Data sampling acts as a pivotal role in training deep learning models. However, an effective sampling schedule is difficult to learn due to the inherently high dimension of parameters in learning the sampling schedule. In this paper, we propose an AutoSampling method to automatically learn sampling schedules for model training, which consists of the multi-exploitation step aiming for optimal local sampling schedules and the exploration step for the ideal sampling distribution. More specifically, we achieve sampling schedule search with shortened exploitation cycle to provide enough supervision. In addition, we periodically estimate the sampling distribution from the learned sampling schedules and perturb it to search in the distribution space. The combination of two searches allows us to learn a robust sampling schedule. We apply our AutoSampling method to a variety of image classification tasks illustrating the effectiveness of the proposed method.

Related papers

• Swift Sampler: Efficient Learning of Sampler by 10 Parameters [5.595723519561982]
  An effective data sampler assigns proper sampling probability for training data. textbfSS can be applied on large-scale data sets with high efficiency.
  arXiv  Detail & Related papers  (2024-10-08T00:26:29Z)
• Adaptive teachers for amortized samplers [76.88721198565861]
  Amortized inference is the task of training a parametric model, such as a neural network, to approximate a distribution with a given unnormalized density where exact sampling is intractable. Off-policy RL training facilitates the discovery of diverse, high-reward candidates, but existing methods still face challenges in efficient exploration. We propose an adaptive training distribution (the Teacher) to guide the training of the primary amortized sampler (the Student) by prioritizing high-loss regions.
  arXiv  Detail & Related papers  (2024-10-02T11:33:13Z)
• Align Your Steps: Optimizing Sampling Schedules in Diffusion Models [63.927438959502226]
  Diffusion models (DMs) have established themselves as the state-of-the-art generative modeling approach in the visual domain and beyond. A crucial drawback of DMs is their slow sampling speed, relying on many sequential function evaluations through large neural networks. We propose a general and principled approach to optimizing the sampling schedules of DMs for high-quality outputs.
  arXiv  Detail & Related papers  (2024-04-22T18:18:41Z)
• Balanced Data Sampling for Language Model Training with Clustering [96.46042695333655]
  We propose ClusterClip Sampling to balance the text distribution of training data for better model training. Extensive experiments validate the effectiveness of ClusterClip Sampling.
  arXiv  Detail & Related papers  (2024-02-22T13:20:53Z)
• AdaSelection: Accelerating Deep Learning Training through Data Subsampling [27.46630703428186]
  We introduce AdaSelection, an adaptive sub-sampling method to identify the most informative sub-samples within each minibatch. Compared with industry-standard baselines, AdaSelection consistently displays superior performance.
  arXiv  Detail & Related papers  (2023-06-19T07:01:28Z)
• Importance Sampling for Stochastic Gradient Descent in Deep Neural Networks [0.0]
  Importance sampling for training deep neural networks has been widely studied. This paper reviews the challenges inherent to this research area. We propose a metric allowing the assessment of the quality of a given sampling scheme.
  arXiv  Detail & Related papers  (2023-03-29T08:35:11Z)
• Sampling Through the Lens of Sequential Decision Making [9.101505546901999]
  We propose a reward-guided sampling strategy called Adaptive Sample with Reward (ASR) Our approach optimally adjusts the sampling process to achieve optimal performance. Empirical results in information retrieval and clustering demonstrate ASR's superb performance across different datasets.
  arXiv  Detail & Related papers  (2022-08-17T04:01:29Z)
• Optimal Importance Sampling for Federated Learning [57.14673504239551]
  Federated learning involves a mixture of centralized and decentralized processing tasks. The sampling of both agents and data is generally uniform; however, in this work we consider non-uniform sampling. We derive optimal importance sampling strategies for both agent and data selection and show that non-uniform sampling without replacement improves the performance of the original FedAvg algorithm.
  arXiv  Detail & Related papers  (2020-10-26T14:15:33Z)
• Adaptive Task Sampling for Meta-Learning [79.61146834134459]
  Key idea of meta-learning for few-shot classification is to mimic the few-shot situations faced at test time. We propose an adaptive task sampling method to improve the generalization performance.
  arXiv  Detail & Related papers  (2020-07-17T03:15:53Z)
• Efficient Deep Representation Learning by Adaptive Latent Space Sampling [16.320898678521843]
  Supervised deep learning requires a large amount of training samples with annotations, which are expensive and time-consuming to obtain. We propose a novel training framework which adaptively selects informative samples that are fed to the training process.
  arXiv  Detail & Related papers  (2020-03-19T22:17:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.