Probability in High Dimension

By Ramon van Handel. 2014

381 citations recorded by the source corpus.

Subfields: Environmental Engineering, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/9d3582ae92b9e42db13dbb56d30f782e60068aa9

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Environmental Engineering

In Statistics and Probability

Citations in the corpus

Provable Filter Pruning for Efficient Neural Networks (2019, methodology): “Moreover, there are m (cid:48) + m random variables, thus, applying McDiarmid’s inequality (van Handel, 2014), we obtain More speciﬁcally, recall that The performance of our approach on a LeNet300-100 architecture trained on MNIST with no derandomization (denoted by "rand"), with partial…”
Uniform Hanson-Wright type concentration inequalities for unbounded entries via the entropy method (2018, neutral): “K and this implies (see van Handel (2016)) that for all λ ∈ R Ent(exp(λ(ϕ(X) − Eϕ(X)))) .”
Chaining Mutual Information and Tightening Generalization Bounds (2018, methodology): “Generalization bounds based on Rademacher complexity and VC-dimension only depend on the hypothesis set and not on the algorithm, effectively rendering them too pessimistic.”
Optimal rates of statistical seriation (2016, background): “The interested readers can ﬁnd the proof, for example, in [vH14, Theorem 5.29], and refer to [LT91] for a more detailed account of the technique.”
Learning a Driving Simulator (2016, background): “As far as we know, this is the ﬁrst paper that tries to learn video predictions from real world highway scenes.”
Estimation and Inference about Heterogeneous Treatment Effects in High-Dimensional Dynamic Panels. (2017, background): “By Azuma’s Lemma (see. e.g., Lemma 3.7 in van Handel (2014)), ENT (Vit)j(d̂i(Xit) − di0(Xit))k is m2NT,∞(π ∞ NT ) 2 NT -subGaussian.”
Sub‐Weibull distributions: Generalizing sub‐Gaussian and sub‐Exponential properties to heavier tailed distributions (2019, neutral): “…of probability and statistics, including concentration, transportation and PAC-Bayes inequalities (Boucheron et al., 2013; Raginsky and Sason, 2013; van Handel, 2014; Catoni, 2007), the missing mass problem (Ben-Hamou et al., 2017), bandit problems (Bubeck and Cesa-Bianchi, 2012) and singular…”
Cutoff for non-negatively curved Markov chains (2021, methodology): “, [24, 41, 61] and the references therein), their application to cutoff seems new and promising.”
Towards Robust and Reliable Algorithmic Recourse (2021, methodology): “Assuming a bounded metric on X , we can upper bound the RHS using Lemma 2 from van Handel [27] which gives us our bound.”