Takimoto et al., 2000 - Google Patents

The last-step minimax algorithm

Takimoto et al., 2000

View PDF
Document ID
15710344759469848895
Author
Takimoto E
Warmuth M
Publication year
Publication venue
Algorithmic Learning Theory: 11th International Conference, ALT 2000 Sydney, Australia, December 11–13, 2000 Proceedings 11

External Links

Snippet

We consider on-line density estimation with a parameterized density from an exponential family. In each trial t the learner predicts a parameter θ t. Then it receives an instance xt chosen by the adversary and incurs loss-ln p (χ t| θ t which is the negative log-likelihood of χ …
Continue reading at www.researchgate.net (PDF) (other versions)

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/62—Methods or arrangements for recognition using electronic means
    • G06K9/6217—Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/62—Methods or arrangements for recognition using electronic means
    • G06K9/6296—Graphical models, e.g. Bayesian networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for programme control, e.g. control unit
    • G06F9/06—Arrangements for programme control, e.g. control unit using stored programme, i.e. using internal store of processing equipment to receive and retain programme
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F1/00—Details of data-processing equipment not covered by groups G06F3/00 - G06F13/00, e.g. cooling, packaging or power supply specially adapted for computer application
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F7/00—Methods or arrangements for processing data by operating upon the order or content of the data handled
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F2207/00—Indexing scheme relating to methods or arrangements for processing data by operating upon the order or content of the data handled

Similar Documents

Publication Publication Date Title
Barnes et al. Lower bounds for learning distributions under communication constraints via fisher information
Takimoto et al. The last-step minimax algorithm
Schölkopf et al. A generalized representer theorem
Tong et al. Active learning for structure in Bayesian networks
Buntine Estimating likelihoods for topic models
Hsu et al. Mixing time estimation in reversible markov chains from a single sample path
US20050119829A1 (en) Robust bayesian mixture modeling
Haussler et al. How well do Bayes methods work for on-line prediction of f+ 1; 1g values
Morvai et al. On universal algorithms for classifying and predicting stationary processes
De Sa et al. Minibatch Gibbs sampling on large graphical models
Temlyakov Approximation in learning theory
Hennig Fixed point clusters for linear regression: computation and comparison
JP2000010961A (en) Device and method for estimating data generation probability and recording medium
Kang et al. Fast simulation for multifactor portfolio credit risk in the t-copula model
Ben-David et al. Agnostic boosting
Chen et al. Corruption robust active learning
Takimoto½ et al. The Last-Ëtep Minimax Algorithm
Han et al. Optimal prediction of markov chains with and without spectral gap
Warmuth et al. Leaving the span
Huang et al. Denoising diffusion probabilistic models are optimally adaptive to unknown low dimensionality
Herbster et al. Online multitask learning with long-term memory
Chen et al. Active online domain adaptation
Milman et al. Geometric parameters in learning theory
Harremoës et al. Convergence of Markov chains in information divergence
Puolamäki et al. Bayesian solutions to the label switching problem