Weighted last-step min-max algorithm with improved sub-logarithmic regret (Q465257): Difference between revisions

From MaRDI portal
Importer (talk | contribs)
Created a new Item
 
Import241208061232 (talk | contribs)
Normalize DOI.
 
(7 intermediate revisions by 7 users not shown)
Property / DOI
 
Property / DOI: 10.1016/j.tcs.2014.09.028 / rank
Normal rank
 
Property / Mathematics Subject Classification ID
 
Property / Mathematics Subject Classification ID: 68T05 / rank
 
Normal rank
Property / Mathematics Subject Classification ID
 
Property / Mathematics Subject Classification ID: 68W27 / rank
 
Normal rank
Property / zbMATH DE Number
 
Property / zbMATH DE Number: 6362898 / rank
 
Normal rank
Property / zbMATH Keywords
 
online learning
Property / zbMATH Keywords: online learning / rank
 
Normal rank
Property / zbMATH Keywords
 
regression
Property / zbMATH Keywords: regression / rank
 
Normal rank
Property / zbMATH Keywords
 
min-max learning
Property / zbMATH Keywords: min-max learning / rank
 
Normal rank
Property / describes a project that uses
 
Property / describes a project that uses: AdaGrad / rank
 
Normal rank
Property / MaRDI profile type
 
Property / MaRDI profile type: MaRDI publication profile / rank
 
Normal rank
Property / full work available at URL
 
Property / full work available at URL: https://doi.org/10.1016/j.tcs.2014.09.028 / rank
 
Normal rank
Property / OpenAlex ID
 
Property / OpenAlex ID: W2179980973 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Relative loss bounds for on-line density estimation with the exponential family of distributions / rank
 
Normal rank
Property / cites work
 
Property / cites work: Performance of adaptive estimation algorithms in dependent random environments / rank
 
Normal rank
Property / cites work
 
Property / cites work: Online Regression Competitive with Changing Predictors / rank
 
Normal rank
Property / cites work
 
Property / cites work: A Second-Order Perceptron Algorithm / rank
 
Normal rank
Property / cites work
 
Property / cites work: Prediction, Learning, and Games / rank
 
Normal rank
Property / cites work
 
Property / cites work: Adaptive regularization of weight vectors / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q3174156 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q5396673 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q4934335 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Prediction in the worst case / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q5689624 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q4633809 / rank
 
Normal rank
Property / cites work
 
Property / cites work: 10.1162/153244301753683726 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Exponentiated gradient versus gradient descent for linear predictors / rank
 
Normal rank
Property / cites work
 
Property / cites work: A game theory approach to constrained minimax state estimation / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q4473253 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Re-adapting the Regularization of Weights for Non-stationary Regression / rank
 
Normal rank
Property / cites work
 
Property / cites work: Competitive On-line Statistics / rank
 
Normal rank
Property / cites work
 
Property / cites work: An identity for kernel ridge regression / rank
 
Normal rank
Property / DOI
 
Property / DOI: 10.1016/J.TCS.2014.09.028 / rank
 
Normal rank
links / mardi / namelinks / mardi / name
 

Latest revision as of 18:20, 9 December 2024

scientific article
Language Label Description Also known as
English
Weighted last-step min-max algorithm with improved sub-logarithmic regret
scientific article

    Statements

    Weighted last-step min-max algorithm with improved sub-logarithmic regret (English)
    0 references
    0 references
    0 references
    31 October 2014
    0 references
    online learning
    0 references
    regression
    0 references
    min-max learning
    0 references

    Identifiers