Enable JavaScript to see more content

1 |
| Related: TFIDF [1706.10207] Optimization Methods for Supervised Machine Learning: From Linear Models to Deep Learning[1909.01994] Quasi-Newton Optimization Methods For Deep Learning Applications[1909.01994v1] Quasi-Newton Optimization Methods For Deep Learning Applications[1706.04769] Stochastic Training of Neural Networks via Successive Convex Approximations[1606.04838] Optimization Methods for Large-Scale Machine Learning[1811.02693] Deep Reinforcement Learning via L-BFGS Optimization[1805.08095] Small steps and giant leaps: Minimal Newton solvers for Deep Learning[1508.02087] A Linearly-Convergent Stochastic L-BFGS Algorithm[1807.00172] Algorithms for solving optimization problems arising from deep neural net models: smooth problems[1904.05856] Connections Between Adaptive Control and Optimization in Machine Learning Mentions [1601.04738] Sub-Sampled Newton Methods II: Local Convergence Rates[1502.04623] DRAW: A Recurrent Neural Network For Image Generation[1601.06759] Pixel Recurrent Neural Networks[1511.06434] Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks[1712.07628] Improving Generalization Performance by Switching from Adam to SGD[1312.5602] Playing Atari with Deep Reinforcement Learning[1609.04747] An overview of gradient descent optimization algorithms[1412.1193] New insights and perspectives on the natural gradient method[1711.05101] Decoupled Weight Decay Regularization[1709.04546] Normalized Direction-preserving Adam[1801.01078] Recent Advances in Recurrent Neural Networks[1509.02971] Continuous control with deep reinforcement learning[1701.07274] Deep Reinforcement Learning: An Overview[1409.2329] Recurrent Neural Network Regularization[1509.03025] Fast low-rank estimation by projected gradient descent: General statistical and algorithmic guarantees[1606.01316] Provable Burer-Monteiro factorization for a class of norm-constrained matrix problems[1412.8729] High Dimensional Expectation-Maximization Algorithm: Statistical Optimization and Asymptotic Normality[1609.04836] On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima[1412.3555] Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling Related: Semantic Math [1904.10523] A neural network-based framework for financial model calibration[1904.10523v1] A neural network-based framework for financial model calibration[1904.10523] A neural network-based framework for financial model calibration[1904.10523v1] A neural network-based framework for financial model calibration[1706.03267] An Alternative to EM for Gaussian Mixture Models: Batch and Stochastic Riemannian Optimization[1603.05486] A flexible state space model for learning nonlinear dynamical systems[1603.05486] A flexible state space model for learning nonlinear dynamical systems[1510.04822] SGD with Variance Reduction beyond Empirical Risk Minimization[1510.04822] SGD with Variance Reduction beyond Empirical Risk Minimization[1612.09158] The interplay between system identification and machine learning |