Information, divergence and risk for binary experiments
From MaRDI portal
Abstract: We unify f-divergences, Bregman divergences, surrogate loss bounds (regret bounds), proper scoring rules, matching losses, cost curves, ROC-curves and information. We do this by systematically studying integral and variational representations of these objects and in so doing identify their primitives which all are related to cost-sensitive binary classification. As well as clarifying relationships between generative and discriminative views of learning, the new machinery leads to tight and more general surrogate loss bounds and generalised Pinsker inequalities relating f-divergences to variational divergence. The new viewpoint illuminates existing algorithms: it provides a new derivation of Support Vector Machines in terms of divergences and relates Maximum Mean Discrepancy to Fisher Linear Discriminants. It also suggests new techniques for estimating f-divergences.
Recommendations
Cited in
(53)- On surrogate loss functions and \(f\)-divergences
- Forecaster's dilemma: extreme events and forecast evaluation
- Calibrated asymmetric surrogate losses
- Multiclass classification, information, divergence and surrogate risk
- Minimax optimal sequential hypothesis tests for Markov processes
- A Steiner formula in the \(L_p\) Brunn Minkowski theory
- Surrogate regret bounds for generalized classification performance metrics
- Divergence for \(s\)-concave and log concave functions
- Potential statistical evidence in experiments and Renyi information
- A theory of learning with corrupted labels
- Some universal insights on divergences for statistics, machine learning and artificial intelligence
- scientific article; zbMATH DE number 7255066 (Why is no real title available?)
- The Bregman proximal average
- Calibrating sufficiently
- A proximal average for prox-bounded functions
- Support vector machines based on convex risk functions and general norms
- Mixed f-divergence and inequalities for log-concave functions
- Beyond Fano's inequality: bounds on the optimal F-score, BER, and cost-sensitive risk and their implications
- A spectral estimation framework for phase retrieval via Bregman divergence minimization
- A historical perspective on Schützenberger-Pinsker inequalities
- Quantum \(f\)-divergences via Nussbaum-Szkoła distributions and applications to \(f\)-divergence inequalities
- A historical perspective on Schützenberger-Pinsker inequalities (extended version)
- A connection between learning to reject and Bhattacharyya divergences
- Authors' reply to the discussion of `safe testing'
- Zihao Wen and David L. Dowe's contribution to the discussion of `safe testing' by Grünwald, de Heide, and Koolen
- Maozai Tian, Keming Yu and Jiangfeng Wang's contribution to the discussion of `safe testing' by Grünwald, de Heide, and Koolen
- Andrej Srakar's contribution to the discussion of `safe testing' by Grünwald, de Heide, and Koolen
- Judith ter Schure's contribution to the discussion of `safe testing' by Grünwald, de Heide, and Koolen
- Christian P. Robert and Joshua Bon's contribution to the discussion of `safe testing' by Grünwald, de Heide, and Koolen
- Stefano Rizzelli's contribution to the discussion of `safe testing' by Grünwald, de Heide, and Koolen
- Luigi Pace and Alessandra Salvan's contribution to the discussion of `safe testing' by Grünwald, de Heide, and Koolen
- Joris Mulder's contribution to the discussion of `safe testing' by Grünwald, de Heide, and Koolen
- Alexander Ly's contribution to the discussion of `safe testing' by Grünwald, de Heide, and Koolen
- Sander Greenland's contribution to the discussion of `safe testing' by Grünwald, de Heide, and Koolen
- Neil Dey, Ryan Martin, and Jonathan P. Williams' contribution to the discussion of `safe testing' by Grünwald, de Heide, and Koolen
- Christine P. Chai's contribution to the discussion of `safe testing' by Grünwald, de Heide, and Koolen
- Marco Cattaneo's contribution to the discussion of ``Safe testing by Grünwald, de Heide, and Koolen
- Joshua bon and christian P. Robert's contribution to the discussion of `safe testing' by Grünwald, de Heide, and Koolen
- Vladimir Vovk's contribution to the discussion of `safe testing' by Grünwald, de Heide, and Koolen
- Wenkai Xu's contribution to the discussion of `safe testing' by Grünwald, de Heide and Koolen
- Christian Hennig's contribution to the discussion of `safe testing' by Grünwald, de Heide, and Koolen
- Glenn Shafer's contribution to the discussion of `safe testing' by Grünwald, de Heide, and Koolen
- Thorsten Dickhaus's contribution to the discussion of `safe testing' by Grünwald, de Heide, and Koolen
- Martin larsson, aaditya ramdas, and johannes Ruf's contribution to the discussion of `safe testing' by Grünwald, de heide, and koolen
- David R. Bickel's contribution to the discussion of `safe testing' by Grünwald, de Heide, and Koolen
- Seconder of the vote of thanks to Grünwald, de Heide, and Koolen and contribution to the discussion of `safe testing'
- Proposer of the vote of thanks to Grünwald, de Heide, and Koolen and contribution to the discussion of `safe testing'
- Safe testing
- Distributionally robust optimization
- A new minimax theorem for randomized algorithms
- Foundations of bare-simulation optimization of distances
- Geometry and stability of supervised learning problems
- Generalized twin Gaussian processes using Sharma-Mittal divergence
This page was built for publication: Information, divergence and risk for binary experiments
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5396625)
