mlsanityData to 7 Oct 2026

Active Labeling: Streaming Stochastic Gradients

arXiv 2205.13255 ↗First posted 26 May 2022cs.LG cs.AI cs.IRcited by 3

Not on the map. Why?

Abstract (arXiv)

The workhorse of machine learning is stochastic gradient descent. To access stochastic gradients, it is common to consider iteratively input/output pairs of a training dataset. Interestingly, it appears that one does not need full supervision to access stochastic gradients, which is the main motivation of this paper. After formalizing the "active labeling" problem, which focuses on active learning with partial supervision, we provide a streaming technique that provably minimizes the ratio of generalization error over the number of samples. We illustrate our technique in depth for robust regression.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 21 of its 86 references that are in the map. First posted on arXiv 26 May 2022.

Builds on

21 of 86 references.

References · 21

  1. 2014Convex Optimization: Algorithms and Complexitycited by 569
  2. 2017Snorkel: Rapid Training Data Creation with Weak Supervisioncited by 370
  3. 2016Optimal Best Arm Identification with Fixed Confidencecited by 233
  4. 2016A vector-contraction inequality for Rademacher complexitiescited by 141
  5. 2013Non-strongly-convex smooth stochastic approximation with convergence rate O(1/n)cited by 110
  6. 2018Preference-based Online Learning with Dueling Bandits: A Surveycited by 100
  7. 2019Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognitioncited by 95
  8. 2015Less is More: Nystr"om Computational Regularizationcited by 89
  9. 2019Sequential Experimental Design for Transductive Linear Banditscited by 88
  10. 2020Kernel methods through the roof: handling billions of points efficientlycited by 88
  11. 2018Statistical Optimality of Stochastic Gradient Descent on Hard Learning Problems through Multiple Passescited by 69
  12. 2015The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognitioncited by 48
9 more
  1. 2020A General Framework for Consistent Structured Prediction with Implicit Loss Embeddingscited by 35
  2. 2020Structured Prediction with Partial Labelling through the Infimum Losscited by 34
  3. 2018Dynamic Pricing with Finitely Many Unknown Valuationscited by 23
  4. 2021Efficient Algorithms for Learning from Coarse Labelscited by 21
  5. 2020Overcoming the curse of dimensionality with Laplacian regularization in semi-supervised learningcited by 14
  6. 2017Exponential convergence of testing error for stochastic gradient methodscited by 13
  7. 2021Fast rates in structured predictioncited by 11
  8. 2019Sorted Top-k in Roundscited by 4
  9. 2019Efficient Primal-Dual Algorithms for Large-Scale Multiclass Classificationcited by 3

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 1.

3 papers.

  1. 2023Active Self-Supervised Learning: A Few Low-Cost Relationships Are All You Needcited by 9
  2. 2024Mode Estimation with Partial Feedbackcited by 1
  3. 2022From Weakly Supervised Learning to Active Learningcited by 0