Algorithmic Learning in a Random World

By Vladimir G Vovk, A. Gammerman, Glenn Shafer. 2005

2,378 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Statistical Learning Theory

How researchers see this paper

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

In Artificial Intelligence

In Information Systems

In Statistical Learning Theory

Citations in the corpus

Consistent Accelerated Inference via Confident Adaptive Transformers (2021, methodology): “Our approach builds on conformal prediction (CP), a model-agnostic and distribution-free framework for creating well-calibrated predictions (Vovk et al., 2005).”
Deep Weighted Averaging Classifiers (2018, background): “For more details, please refer to [53, 54].”
A tutorial on conformal prediction (2007, background): “But the efficiency of conformal prediction will depend on Q and the nonconformity measure.”
Information, Divergence and Risk for Binary Experiments (2009, background): “Overarching frameworks: These include Bayesian (Robert, 1994), information-theoretic (Jenssen, 2005a; Harremoës, 1993), game-theoretic (Vovk et al., 2005; Grünwald and Dawid, 2004), MDL (Grünwald, 2007; Rissanen, 2007), regularised distance minimisation (Borwein and Lewis, 1991; Altun and Smola, 200”
Confident Adaptive Language Modeling (2022, methodology): “Our calibration procedure for connecting global constraints to local decisions, relates to recent research around distribution-free uncertainty quantiﬁcation [1; 62; 77].”
Aleatoric and epistemic uncertainty in machine learning: an introduction to concepts and methods (2019, background): “Conformal prediction (Vovk et al., 2003; Shafer and Vovk, 2008; Balasubramanian et al., 2014) is a framework for reliable prediction that is rooted in classical frequentist statistics, more specifically in hypothesis testing.”
Knowing what you know: valid confidence sets in multiclass and multilabel prediction (2020, methodology): “[33]), we expect the quantile estimator (5) in the CQC method 1 to better account for data heterogeneity, maintaining higher coverage on subsets of the data.”
Knowing what You Know: valid and validated confidence sets in multiclass and multilabel prediction (2020, methodology): “…conﬁdence sets, we show how to also construct a small number of sets in/out that similarly satisfy P ( ∪ i { C 1.2 Related work and background Vovk et al. (2005) introduce (split-)conformal inference, which splits the ﬁrst n samples of the exchangeable pairs { ( X i , Y i ) } n +1 i =1 into…”
Localized Conformal Prediction: A Generalized Inference Framework for Conformal Prediction (2021, background): “…+1 , Y n +1 ) as the ( n + 1) th observation, CP achieves (1.1) under the assumption that Z n +1 is also independently generated from P XY , without additional distributional assumptions on P XY itself (Vovk et al. 2005, Shafer & Vovk 2008, Vovk et al. 2009, Lei & Wasserman 2014, Lei et al. 2018).”
Least Ambiguous Set-Valued Classifiers With Bounded Error Levels (2016, methodology): “…plug-in estimators in Section 4, together with a technique called inductive conformal inference (Papadopoulos, Proedrou, Vovk, and Gammerman 2002; Vovk, Gammerman, and Shafer 2005; Shafer and Vovk 2008; Vovk 2013) or split-conformal inference (Lei, Rinaldo, andWasserman 2014), whichwe use to…”
Inductive Conformal Prediction: Theory and Application to Neural Networks (2008, background): “This Section gives an outline of the main idea behind conformal prediction; for more details see (Vovk et al., 2005).”
Alignment for Advanced Machine Learning Systems (2020, background): “Conformal prediction (Vovk, Gammerman, and Shafer 2005) is an alternative non-Bayesian approach that attempts to produce well-calibrated predictions.”
Bernstein's inequalities for general Markov chains (2018, positive): “Recent studies, such as those in conformal prediction, have leveraged this modeling (Vovk et al., 2005).”
Random Forest ensembles for detection and prediction of Alzheimer's disease with a good between-cohort robustness (2014, positive): “…may be bene ﬁ cial in this context, providing not only an opportunity to update the models, but also valid estimations of the prediction con ﬁ dence under a general i.i.d. assumption (independent and identically distributed) (Vovk, 2005; Gammerman and Vovk, 2007; Nouretdinov and Lebedev, 2013).”
With Malice Towards None: Assessing Uncertainty via Equalized Coverage (2019, methodology): “We refer the reader to [20, 23] for more details about transductive conformal prediction, its advantages and limitations.”
Kernel Ridge Regression (2013, methodology): “The second example belongs to the area of conformal prediction [17] and only depends on the assumption of randomness.”
Adaptive Conformal Inference Under Distribution Shift (2021, methodology): “By introducing additional randomization this generic procedure can be altered slightly to produce a set Ĉt that satisfies the exact marginal coverage guarantee P(Yt 2 Ĉt) = 1 ↵ [34].”
Classification with Valid and Adaptive Coverage (2020, methodology): “5 Extension to label-conditional coverage Our method can be easily extended to obtain provable coverage separately for each class [19, 24]: P [ Yn+1 ∈ Ĉn,α(Xn+1) | Yn+1 = y ] ≥ 1− α, ∀y ∈ Y.”