mlsanityData to 7 Oct 2026

Stochastic Perturbations of Tabular Features for Non-Deterministic Inference with Automunge

arXiv 2202.09248 ↗First posted 18 Feb 2022cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Injecting gaussian noise into training features is well known to have regularization properties. This paper considers noise injections to numeric or categoric tabular features as passed to inference, which translates inference to a non-deterministic outcome and may have relevance to fairness considerations, adversarial example protection, or other use cases benefiting from non-determinism. We offer the Automunge library for tabular preprocessing as a resource for the practice, which includes options to integrate random sampling or entropy seeding with the support of quantum circuits, representing a new way to channel quantum algorithms into classical learning.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 27 of its 81 references that are in the map. First posted on arXiv 18 Feb 2022.

Builds on

27 of 81 references.

References · 27

  1. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  2. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  3. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  4. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  5. 2020Variational Quantum Algorithmscited by 687
  6. 2017The Effectiveness of Data Augmentation in Image Classification using Deep Learningcited by 368
  7. 2020The effect of data encoding on the expressive power of variational quantum machine learning modelscited by 328
  8. 2018Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learningcited by 278
  9. 2018Adversarial Logit Pairingcited by 224
  10. 2018CatBoost: gradient boosting with categorical features supportcited by 208
  11. 2021Well-tuned Simple Nets Excel on Tabular Datasetscited by 151
  12. 2019Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneckcited by 101
15 more
  1. 2021SubTab: Subsetting Features of Tabular Data for Self-Supervised Representation Learningcited by 101
  2. 2016Robustness of classifiers: from adversarial to random noisecited by 87
  3. 2021Noisy intermediate-scale quantum (NISQ) algorithmscited by 79
  4. 2013Stochastic Pooling for Regularization of Deep Convolutional Neural Networkscited by 48
  5. 2021Noisy Recurrent Neural Networkscited by 42
  6. 2020Explicit Regularisation in Gaussian Noise Injectionscited by 37
  7. 2019Exact expressions for double descent and implicit regularization via surrogate random designcited by 35
  8. 2016Edward: A library for probabilistic modeling, inference, and criticismcited by 28
  9. 2014Analyzing noise in autoencoders and deep networkscited by 25
  10. 2021On the Inherent Regularization Effects of Noise Injection During Trainingcited by 18
  11. 2021Circa: Stochastic ReLUs for Private Deep Learningcited by 16
  12. 2021Flexible FOND Planning with Explicit Fairness Assumptionscited by 6
  13. 2021On Data-centric Mythscited by 4
  14. 2018How Much Data Do You Need? An Operational, Pre-Asymptotic Metric for Fat-tailednesscited by 1
  15. 2021Adaptive Multi-View ICA: Estimation of noise levels for optimal inferencecited by 1

Built on by

Cited by year

Citing papers per year: 2022: 1.

1 paper.

  1. 2022Feature Encodings for Gradient Boosting with Automungecited by 0