mlsanityData to 14 Oct 2026

Statistical and Computational Guarantees for Influence Diagnostics

arXiv 2212.04014 ↗First posted 8 Dec 2022stat.ML cs.LG math.STcited by 1

Not on the map. Why?

Abstract (arXiv)

Influence diagnostics such as influence functions and approximate maximum influence perturbations are popular in machine learning and in AI domain applications. Influence diagnostics are powerful statistical tools to identify influential datapoints or subsets of datapoints. We establish finite-sample statistical bounds, as well as computational complexity bounds, for influence functions and approximate maximum influence perturbations using efficient inverse-Hessian-vector product implementations. We illustrate our results with generalized linear models and large attention based models on synthetic and real data.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 18 of its 57 references that are in the map. First posted on arXiv 8 Dec 2022.

Builds on

18 of 57 references.

References · 18

  1. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  2. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
  3. 2016Pointer Sentinel Mixture Modelscited by 3,096
  4. 2017Understanding Black-box Predictions via Influence Functionscited by 1,741
  5. 2021Editing Factual Knowledge in Language Modelscited by 553
  6. 2017Zero-Shot Relation Extraction via Reading Comprehensioncited by 426
  7. 2016Katyusha: The First Direct Acceleration of Stochastic Gradient Methodscited by 135
  8. 2021Scaling Up Influence Functionscited by 132
  9. 2018A Swiss Army Infinitesimal Jackknifecited by 54
  10. 2013A Statistical Perspective on Algorithmic Leveragingcited by 39
  11. 2015Variance Reduced Stochastic Gradient Descent with Neighborscited by 39
  12. 2017Catalyst Acceleration for First-order Convex Optimization: from Theory to Practicecited by 39
6 more
  1. 2018Finite-sample analysis of M-estimators using self-concordancecited by 30
  2. 2020An Automatic Finite-Sample Robustness Metric: When Can Dropping a Little Data Make a Big Difference?cited by 27
  3. 2017A Markov Chain Theory Approach to Characterizing the Minimax Optimality of Stochastic Gradient Descent (for Least Squares)cited by 26
  4. 2022Superquantiles at Work: Machine Learning Applications and Efficient Subgradient Computationcited by 10
  5. 2018Small steps and giant leaps: Minimal Newton solvers for Deep Learningcited by 6
  6. 2022The Influence Function of Graphical Lasso Estimatorscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Influence Diagnostics in High-dimensional M-estimation: Precise Asymptoticscited by 0