Stochastic Methods

DETOX: A Redundancy-based Framework for Faster and More Robust Gradient Aggregation NeurIPS 2019 Fluctuation-dissipation relations for stochastic gradient descent ICLR 2019 Making Asynchronous Stochastic Gradient Descent Work for Transformers EMNLP 2019 Momentum-Based Variance Reduction in Non-Convex SGD NeurIPS 2019 Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learning AAAI 2019 Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification and Local Computations NeurIPS 2019 Quasi-hyperbolic momentum and Adam for deep learning ICLR 2019 Reducing Noise in GAN Training with Variance Reduced Extragradient NeurIPS 2019 Sampled Softmax with Random Fourier Features NeurIPS 2019 Scalable and Efficient Pairwise Learning to Achieve Statistical Accuracy AAAI 2019 Stochastic Runge-Kutta Accelerates Langevin Monte Carlo and Beyond NeurIPS 2019 Accelerating Asynchronous Stochastic Gradient Descent for Neural Machine Translation EMNLP 2018 A Linear Speedup Analysis of Distributed Deep Learning with Sparse and Quantized Communication NeurIPS 2018 Dimensionality Reduction for Stationary Time Series via Stochastic Nonconvex Optimization NeurIPS 2018 Don't Decay the Learning Rate, Increase the Batch Size ICLR 2018 Evolutionary Stochastic Gradient Descent for Optimization of Deep Neural Networks NeurIPS 2018 How To Make the Gradients Small Stochastically: Even Faster Convex and Nonconvex SGD NeurIPS 2018 LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learning NeurIPS 2018 SPIDER: Near-Optimal Non-Convex Optimization via Stochastic Path-Integrated Differential Estimator NeurIPS 2018 Statistical Tomography of Microscopic Life CVPR 2018 Training Deep Models Faster with Robust, Approximate Importance Sampling NeurIPS 2018 Differentiable Scheduled Sampling for Credit Assignment ACL 2017 Langevin Dynamics with Continuous Tempering for Training Deep Neural Networks NeurIPS 2017 Reducing Reparameterization Gradient Variance NeurIPS 2017 Training Deep Networks without Learning Rates Through Coin Betting NeurIPS 2017