Statistics For High Dimensional Data Methods Theory And

2022

Citations in the corpus

• Practical and Private (Deep) Learning without Sampling or Shuffling (2021, methodology): “[9] Peter Bhlmann and Sara van de Geer.”
• The hardness of conditional independence testing and the generalised covariance measure (2018, methodology): “A notable exception is when f and g are sparse linear functions; in this setting, alternative arguments can be used to show the GCM with Lasso regressions has optimal power when Z has a sparse inverse covariance [41, 46].”
• Continual Learning for Robotics (2019, background): “1 Penalty Computing Regularization is a process of introducing additional information in order to prevent overfitting [14].”
• Statistical inference for model parameters in stochastic gradient descent (2016, methodology): “, [22, 38, 6, 4]), the Lasso estimator can be used as a screening method to reduce the set of the variables to Ŝ, a subset which contains the true support S with probability tending to 1.”
• Spectral Deconfounding and Perturbed Sparse Linear Models (2018, methodology): “One can easily show that under some mild conditions, the sample covariance matrix Σ̂ = X TX n satisfies φ(2) Σ̂ ≥ λmin(Σ) 2 with high probability (see [4]) and we need to ensure that φΣ̃ is bounded away from zero as well.”
• A Critical Review of LASSO and Its Derivatives for Variable Selection Under Dependence Among Covariates (2020, methodology): “If this condition is violated, all that we can hope for is recovery of the regression vector β in an L 2 -sense of convergence by achieving (cid:107) ˆ β L 1 − β (cid:107) 2 −→ p n →∞ 0 (see Meinshausen and Bühlmann (2010) for more details).”
• On cross-validated Lasso in high dimensions (2016, unknown): “5) [0, 5] [6, 10] [11, 15] [16, 20] [21, 25] [26, p] [31, p] [36, p] (n, p)=(100, 40) 0.”