Corpus ID: 221266018

Approximate Cross-Validation with Low-Rank Data in High Dimensions

@article{Stephenson2020ApproximateCW,
  title={Approximate Cross-Validation with Low-Rank Data in High Dimensions},
  author={W. T. Stephenson and Madeleine Udell and T. Broderick},
  journal={ArXiv},
  year={2020},
  volume={abs/2008.10547}
}
  • W. T. Stephenson, Madeleine Udell, T. Broderick
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • Many recent advances in machine learning are driven by a challenging trifecta: large data size $N$; high dimensions; and expensive algorithms. In this setting, cross-validation (CV) serves as an important tool for model assessment. Recent advances in approximate cross validation (ACV) provide accurate approximations to CV with only a single model fit, avoiding traditional CV's requirement for repeated runs of expensive algorithms. Unfortunately, these ACV methods can lose both speed and… CONTINUE READING

    References

    SHOWING 1-10 OF 34 REFERENCES
    Approximate Cross-Validation in High Dimensions with Guarantees
    • 6
    • PDF
    Approximate Cross-validation: Guarantees for Model Assessment and Selection
    • 5
    • PDF
    Cross validation in LASSO and its acceleration
    • 25
    • PDF
    On Optimal Generalizability in Parametric Learning
    • 26
    • Highly Influential
    • PDF
    A Swiss Army Infinitesimal Jackknife
    • 30
    • PDF
    A scalable estimate of the extra-sample prediction error via approximate leave-one-out
    • 17
    • PDF
    Fixed-Rank Approximation of a Positive-Semidefinite Matrix from Streaming Data
    • 27
    • PDF
    Optimizing Millions of Hyperparameters by Implicit Differentiation
    • 30
    • PDF
    Understanding Black-box Predictions via Influence Functions
    • 873
    • PDF