deep learning optimization 딥러닝 pytorch 파이토치 sgd 최적화 rnn Gradient descent Linear Algebra neural network convex Stochastic Process duality Random Process convergence 선형대수학 gradient ADAM CNN measure theory 수학자료 information geometry convergence analysis random reshuffling non-convex non-convex optimization Mirror descent Fenchel conjugate Natural gradient Fisher information RESNET probability theory Regularization hessian cross-entropy tensor TRANSFORMER Momentum 인공지능 log likelihood Martingale optional stopping theorem Martinglae stochastic gradient high probability almost sure exponential family distribution 정보기하학 distributions exponential family inequality cookbook concentraion inequality Inequlaity local SGD convergence analyis Adaptive moment estimator adaptive step size Second order optimization proximal operator convex conjugate Lagrangian function lagrangian convex optimization empirical Fisher Fisher information matrix gradient vanishing problem Inception Module Hessian matrix convergence rate Strong convex Embedding vector 딥러닝 수학 Sequence data 위상수학 Distributed learning Federated learning layer normalization 딥러닝 최적화 eigenvector ISTA Nesterov Momentum Markov AdaGrad bias-variance vgg dual problem Probability Distribution 지수족 skip connection 고유벡터 고윳값 Newton's Method GoogLeNet AlexNet calculus lasso Smoothness 경사 하강법 dropout rmsprop Stochastic Gradient Descent 볼록 eigenvalue backpropagation KL-Divergence supervised Attention Mechanism 손실함수 LeNet 확률통계 경사하강법 topology manifold cookbook GAN LSTM Batch Normalization overfitting objective function ODE primal Dual noise Training statistics probability Machine Learning Word2Vec 확률분포 신경망 Ridge AI 머신러닝 ANALYSIS Smooth GD 학습