mlsanityData to 14 Oct 2026

Scaffolding Sets

arXiv 2111.03135 ↗First posted 4 Nov 2021cs.LG cs.DS stat.MLcited by 8

Not on the map. Why?

Abstract (arXiv)

Predictors map individual instances in a population to the interval [0,1]. For a collection mathcal C of subsets of a population, a predictor is multi-calibrated with respect to mathcal C if it is simultaneously calibrated on each set in mathcal C. We initiate the study of the construction of scaffolding sets, a small collection mathcal S of sets with the property that multi-calibration with respect to mathcal S ensures correctness, and not just calibration, of the predictor. Our approach is inspired by the folk wisdom that the intermediate layers of a neural net learn a highly structured and useful data representation.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 33 of its 64 references that are in the map. First posted on arXiv 4 Nov 2021.

Builds on

33 of 64 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2017On Calibration of Modern Neural Networkscited by 4,960
  4. 2016Distribution-Free Predictive Inference For Regressioncited by 668
  5. 2019Conformalized Quantile Regressioncited by 629
  6. 2016Inherent Trade-Offs in the Fair Determination of Risk Scorescited by 586
  7. 2017Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairnesscited by 384
  8. 2019Gradient Descent Maximizes the Margin of Homogeneous Neural Networkscited by 320
  9. 2019Verified Uncertainty Calibrationcited by 309
  10. 2019On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networkscited by 305
  11. 2015Highway Networkscited by 260
  12. 2021Understanding self-supervised Learning Dynamics without Contrastive Pairscited by 256
21 more
  1. 2020Few-Shot Learning via Learning the Representation, Provablycited by 214
  2. 2020On the Theory of Transfer Learning: The Importance of Task Diversitycited by 186
  3. 2015The Power of Depth for Feedforward Neural Networkscited by 183
  4. 2020Provable Meta-Learning of Linear Representationscited by 161
  5. 2020Predicting What You Already Know Helps: Provable Self-Supervised Learningcited by 152
  6. 2017Learning One-hidden-layer Neural Networks with Landscape Designcited by 81
  7. 2021Calibrating Predictions to Decisions: A Novel Approach to Multi-Class Calibrationcited by 79
  8. 2020Outcome Indistinguishabilitycited by 75
  9. 2021Omnipredictorscited by 74
  10. 2020Moment Multicalibration for Uncertainty Estimationcited by 63
  11. 2021When and How Mixup Improves Calibrationcited by 60
  12. 2021The Power of Contrast for Feature Learning: A Theoretical Analysiscited by 53
  13. 2019Metric Learning for Individual Fairnesscited by 52
  14. 2021Online Multivalid Learning: Means, Moments, and Prediction Intervalscited by 49
  15. 2021Top-label calibration and multiclass-to-binary reductionscited by 46
  16. 2021Distribution-free calibration guarantees for histogram binning without sample splittingcited by 45
  17. 2021Adversarial Training Helps Transfer Learning via Better Representationscited by 36
  18. 2018Learning Two-layer Neural Networks with Symmetric Inputscited by 22
  19. 2018Minimax optimal rates for Mondrian trees and forestscited by 18
  20. 2019An Algorithmic Framework for Fairness Elicitationcited by 16
  21. 2014Analysis of purely random forests biascited by 10

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 6.

8 papers.

  1. 2023How Does Information Bottleneck Help Deep Learning?cited by 93
  2. 2023Understanding Multimodal Contrastive Learning and Incorporating Unpaired Datacited by 43
  3. 2023Multicalibration as Boosting for Regressioncited by 33
  4. 2022Freeze then Train: Towards Provable Representation Learning under Spurious Correlations and Feature Noisecited by 22
  5. 2023HappyMap: A Generalized Multi-calibration Methodcited by 18
  6. 2023Last-Layer Fairness Fine-tuning is Simple and Effective for Neural Networkscited by 17
  7. 2022FIFA: Making Fairness More Generalizable in Classifiers Trained on Imbalanced Datacited by 13
  8. 2023On the Richness of Calibrationcited by 9