stochastic gradient descent

Communication-efficient Distributed SGD with Sketching NeurIPS 2019 Communication trade-offs for Local-SGD with large step size NeurIPS 2019 Computationally and Statistically Efficient Truncated Regression COLT 2019 Conditional Network Embeddings ICLR 2019 Continuous-time Models for Stochastic Optimization Algorithms NeurIPS 2019 Control Batch Size and Learning Rate to Generalize Well: Theoretical and Empirical Evidence NeurIPS 2019 Data Cleansing for Models Trained with SGD NeurIPS 2019 Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication ICML 2019 Deep Frank-Wolfe For Neural Network Optimization ICLR 2019 Deep Layers as Stochastic Solvers ICLR 2019 DeepOBS: A Deep Learning Optimizer Benchmark Suite ICLR 2019 Deep Switch Networks for Generating Discrete Data and Language AISTATS 2019 Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience ICLR 2019 Dimension-Free Bounds for Low-Precision Training NeurIPS 2019 DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-pass Error-Compensated Compression ICML 2019 Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup NeurIPS 2019 Efficient Convex Relaxations for Streaming PCA NeurIPS 2019 Efficient Diversified Mini-Batch Selection using Variable High-layer Features ACML 2019 Efficient Smooth Non-Convex Stochastic Compositional Optimization via Stochastic Recursive Gradient Descent NeurIPS 2019 Empirical Risk Minimization and Stochastic Gradient Descent for Relational Data AISTATS 2019 Error Feedback Fixes SignSGD and other Gradient Compression Schemes ICML 2019 Estimate Sequences for Variance-Reduced Stochastic Composite Optimization ICML 2019 Exchangeability and Kernel Invariance in Trained MLPs IJCAI 2019 Explicitly Imposing Constraints in Deep Networks via Conditional Gradients Gives Improved Generalization and Faster Convergence AAAI 2019 Exponentially convergent stochastic k-PCA without variance reduction NeurIPS 2019