グラフ理論

Protected: Thompson Sampling, linear bandit problem on a logistic regression model

Thompson sampling, linear bandit problem on logistic regression models utilized in digital transformation, artificial intelligence, and machine learning tasks (Thompson sampling, maximum likelihood estimation, Laplace approximation, algorithms, Newton's method, negative log posterior probability, gradient vector, Hesse matrix, Laplace approximation, Bayesian statistics, generalized linear models, Lin-UCB measures, riglet upper bound)

2023.04.07

アルゴリズム:Algorithmsグラフ理論スパースモデリングバンディッド問題幾何学:Geometry微分積分:Calculus最適化:Optimization機械学習:Machine Learning確率・統計:Probability and Statistics線形代数:Linear Algebra

Protected: Sparse learning based on group L1 norm regularization

Sparse machine learning based on group L1-norm regularization for digital transformation, artificial intelligence, and machine learning tasks relative dual gap, dual problem, gradient descent, extended Lagrangian function, dual extended Lagrangian method, Hessian, L1-norm regularization, and group L1-norm regularization, dual norm, empirical error minimization problem, prox operator, Nesterov's acceleration method, proximity gradient method, iterative weighted reduction method, variational representation, nonzero group number, kernel weighted regularization term, concave conjugate, regenerative kernel Hilbert space, support vector machine, kernel weight Multi-kernel learning, basis kernel functions, EEG signals, MEG signals, voxels, electric dipoles, neurons, multi-task learning

2023.04.06

アルゴリズム:Algorithmsグラフ理論スパースモデリングスパースモデリング微分積分:Calculus最適化:Optimization機械学習:Machine Learning確率・統計:Probability and Statistics線形代数:Linear Algebra集合論:Set theory

Protected: Optimality conditions for equality-constrained optimization problems in machine learning

Optimality conditions for equality-constrained optimization problems in machine learning utilized in digital transformation, artificial intelligence, and machine learning tasks (inequality constrained optimization problems, effective constraint method, Lagrange multipliers, first order independence, local optimal solutions, true convex functions, strong duality theorem, minimax theorem, strong duality, global optimal solutions, second order optimality conditions, Lagrange undetermined multiplier method, gradient vector, first order optimization problems)

2023.04.05

アルゴリズム:Algorithmsグラフ理論スパースモデリング幾何学:Geometry微分積分:Calculus最適化:Optimization機械学習:Machine Learning確率・統計:Probability and Statistics線形代数:Linear Algebra

Protected: Discriminant Conformal Losses in Multi-Valued Discriminant by Statistical Mathematics Theory and its Application to Various Loss Functions

Discriminant conformal loss of multi-valued discriminant and its application to various loss functions by statistical mathematics theory utilized in digital transformation, artificial intelligence, and machine learning tasks discriminant model loss, discriminant conformal, narrow order preserving properties, logistic model, maximum likelihood estimation, nonnegative convex function, one-to-other loss, constrained comparison loss, convex nonnegative-valued functions, hinge loss, pairwise comparison loss, multivalued surport vector machine, monotone nonincreasing function, predictive discriminant error, predictive ψ-loss, measurable function

2023.04.04

アルゴリズム:Algorithmsグラフ理論スパースモデリング幾何学:Geometry微分積分:Calculus最適化:Optimization機械学習:Machine Learning確率・統計:Probability and Statistics線形代数:Linear Algebra

Protected: Bayesian inference by variational and collapsed Gibbs sampling of Gaussian mixture models

Bayesian inference with variational and collapsed Gibbs sampling of Gaussian mixture models utilized in digital transformation, artificial intelligence, and machine learning tasks inference algorithms, analytic integral approximation, complex models, Gauss-Wishart distribution, clustering, multi-dimensional Student's t-distribution, categorical distribution, Poisson mixture models, Dirichlet distribution, approximate posterior distribution, latent variables

2023.04.03

アルゴリズム:Algorithmsグラフ理論スパースモデリングベイズ推定幾何学:Geometry微分積分:Calculus最適化:Optimization機械学習:Machine Learning確率・統計:Probability and Statistics線形代数:Linear Algebra

Protected: Value Assessment and Policy and Weaknesses in Deep Reinforcement Learning

Value assessment and strategies and weaknesses in deep reinforcement learning used for digital transformation, artificial intelligence, and machine learning tasks poor sample efficiency, difficulty in validating methods as well, impact of implementation practices on performance, library initial values, poor reproducibility, over-training, local optimum, dexterity, TRPO, PPO, continuous value control, image control, policy-based, value-based

2023.03.30

アルゴリズム:Algorithmsグラフ理論スパースモデリング幾何学:Geometry強化学習微分積分:Calculus最適化:Optimization機械学習:Machine Learning深層学習:Deep Learning確率・統計:Probability and Statistics線形代数:Linear Algebra

Protected: Linear Bandit, Contextual Bandit, Linear Bandit Problem with LinUCB Policies

Linear Bandit, Contextual Bandit, LineUCB policy for linear bandit problems (Riglet, algorithm, least squares quantification, LinUCB score, reward expectation, point estimate, knowledge) utilized in digital transformation, artificial intelligence, machine learning tasks utilization-oriented measures, search-oriented measures, Woodbury's formula, LinUCB measures, LinUCB policy, contextual bandit, website optimization, maximum sales expectation, bandit optimal budget allocation)

2023.03.24

アルゴリズム:Algorithmsグラフ理論スパースモデリングバンディッド問題幾何学:Geometry強化学習微分積分:Calculus最適化:Optimization機械学習:Machine Learning確率・統計:Probability and Statistics線形代数:Linear Algebra

Protected: Evaluation of Rademacher Complexity and Prediction Discrimination Error in Multi-Valued Discrimination Using Statistical Mathematics Theory

Rademacher Complexity and Prediction Discriminant Error in Multivalued Discrimination by Statistical Mathematics Theory Used in Digital Transformation, Artificial Intelligence and Machine Learning Tasks Convex quadratic programming problems, mathematical programming, discriminant machines, prediction discriminant error, Bayesian error, multilevel support vector machines, representation theorem,. Rademacher complexity, multilevel marginals, regularization terms, empirical loss, reproducing nuclear Hilbert spaces, norm constraints, Lipschitz continuity, predictive Φp-multilevel marginals loss, empirical Φ-multilevel marginals loss, uniform bounds, discriminant functions, discriminant

2023.03.23

アルゴリズム:Algorithmsグラフ理論スパースモデリング幾何学:Geometry微分積分:Calculus最適化:Optimization機械学習:Machine Learning確率・統計:Probability and Statistics線形代数:Linear Algebra

Protected: Two-Pair Extended Lagrangian and Two-Pair Alternating Direction Multiplier Methods as Optimization Methods for L1-Norm Regularization

Optimization methods for L1 norm regularization in sparse learning utilized in digital transformation, artificial intelligence, and machine learning tasks FISTA, SpaRSA, OWLQN, DL methods, L1 norm, tuning, algorithms, DADMM, IRS, and Lagrange multiplier, proximity point method, alternating direction multiplier method, gradient ascent method, extended Lagrange method, Gauss-Seidel method, simultaneous linear equations, constrained norm minimization problem, Cholesky decomposition, alternating direction multiplier method, dual extended Lagrangian method, relative dual gap, soft threshold function, Hessian matrix

2023.03.22

アルゴリズム:Algorithmsグラフ理論スパースモデリングスパースモデリング幾何学:Geometry微分積分:Calculus最適化:Optimization機械学習:Machine Learning確率・統計:Probability and Statistics線形代数:Linear Algebra集合論:Set theory

Protected: An example of machine learning by Bayesian inference: inference by Gibbs sampling of a Gaussian mixture model

Example of learning Bayesian inference utilized in digital transformation, artificial intelligence, and machine learning tasks: inference with Gibbs sampling of Gaussian mixture models (algorithms, observation models, Poisson mixture models, Wishart distribution, multidimensional Gaussian distribution, conditional distribution, and Gaussian Wishart distribution, latent variable, categorical distribution)

2023.03.21

アルゴリズム:Algorithmsグラフ理論ベイズ推定幾何学:Geometry微分積分:Calculus最適化:Optimization機械学習:Machine Learning確率・統計:Probability and Statistics線形代数:Linear Algebra