| A Distributed Optimisation Framework Combining Natural Gradient with Hessian-Free for Discriminative Sequence Training | Mar 12, 2021 | Automatic Speech RecognitionAutomatic Speech Recognition (ASR) | —Unverified | 0 |
| Learning-Augmented Sketches for Hessians | Feb 24, 2021 | Dimensionality ReductionSecond-order methods | —Unverified | 0 |
| Distributed Second Order Methods with Fast Rates and Compressed Communication | Feb 14, 2021 | Distributed OptimizationSecond-order methods | —Unverified | 0 |
| Kronecker-factored Quasi-Newton Methods for Deep Learning | Feb 12, 2021 | Deep LearningSecond-order methods | —Unverified | 0 |
| Adaptive Single-Pass Stochastic Gradient Descent in Input Sparsity Time | Jan 1, 2021 | Second-order methodsStochastic Optimization | —Unverified | 0 |
| A Chaos Theory Approach to Understand Neural Network Optimization | Jan 1, 2021 | Second-order methods | —Unverified | 0 |
| Noise and Fluctuation of Finite Learning Rate Stochastic Gradient Descent | Dec 7, 2020 | Bayesian InferenceSecond-order methods | —Unverified | 0 |
| Utility Maximization for Large-Scale Cell-Free Massive MIMO Downlink | Sep 15, 2020 | FairnessSecond-order methods | —Unverified | 0 |
| Second-order Neural Network Training Using Complex-step Directional Derivative | Sep 15, 2020 | Deep LearningSecond-order methods | —Unverified | 0 |
| Debiasing Distributed Second Order Optimization with Surrogate Sketching and Scaled Regularization | Jul 2, 2020 | Point ProcessesSecond-order methods | —Unverified | 0 |
| Second-Order Information in Non-Convex Stochastic Optimization: Power and Limitations | Jun 24, 2020 | Second-order methodsStochastic Optimization | —Unverified | 0 |
| When Does Preconditioning Help or Hurt Generalization? | Jun 18, 2020 | regressionSecond-order methods | —Unverified | 0 |
| A block coordinate descent optimizer for classification problems exploiting convexity | Jun 17, 2020 | ClassificationGeneral Classification | —Unverified | 0 |
| Enhance Curvature Information by Structured Stochastic Quasi-Newton Methods | Jun 17, 2020 | Second-order methods | —Unverified | 0 |
| Learning Rates as a Function of Batch Size: A Random Matrix Theory Approach to Neural Network Training | Jun 16, 2020 | Second-order methods | CodeCode Available | 0 |
| Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective Bayesian Optimization | Jun 9, 2020 | Bayesian OptimizationSecond-order methods | CodeCode Available | 2 |
| SONIA: A Symmetric Blockwise Truncated Optimization Algorithm | Jun 6, 2020 | BIG-bench Machine LearningSecond-order methods | —Unverified | 0 |
| Asymptotic Analysis of Conditioned Stochastic Gradient Descent | Jun 4, 2020 | Second-order methods | CodeCode Available | 0 |
| On the Promise of the Stochastic Generalized Gauss-Newton Method for Training DNNs | Jun 3, 2020 | Second-order methods | CodeCode Available | 0 |
| ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning | Jun 1, 2020 | BIG-bench Machine LearningSecond-order methods | CodeCode Available | 1 |
| MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulation | Mar 27, 2020 | Bilevel OptimizationNeural Architecture Search | CodeCode Available | 1 |
| Critical Point-Finding Methods Reveal Gradient-Flat Regions of Deep Network Losses | Mar 23, 2020 | Second-order methods | —Unverified | 0 |
| Stochastic Subspace Cubic Newton Method | Feb 21, 2020 | Second-order methods | —Unverified | 0 |
| DDPNOpt: Differential Dynamic Programming Neural Optimizer | Feb 20, 2020 | Second-order methods | —Unverified | 0 |
| Low Rank Saddle Free Newton: A Scalable Method for Stochastic Nonconvex Optimization | Feb 7, 2020 | Second-order methods | CodeCode Available | 1 |
| Newtonian Monte Carlo: single-site MCMC meets second-order gradient methods | Jan 15, 2020 | Second-order methodsVariational Inference | CodeCode Available | 0 |
| Curvature-corrected learning dynamics in deep neural networks | Jan 1, 2020 | Second-order methods | —Unverified | 0 |
| Stochastic Newton and Cubic Newton Methods with Simple Local Linear-Quadratic Rates | Dec 3, 2019 | Second-order methods | CodeCode Available | 0 |
| Hierarchical model-based policy optimization: from actions to action sequences and back | Nov 28, 2019 | Second-order methods | —Unverified | 0 |
| Implementation of a modified Nesterov's Accelerated quasi-Newton Method on Tensorflow | Oct 21, 2019 | Second-order methods | —Unverified | 0 |
| Fast and Furious Convergence: Stochastic Second Order Methods under Interpolation | Oct 11, 2019 | Binary ClassificationSecond-order methods | CodeCode Available | 0 |
| EXACT ANALYSIS OF CURVATURE CORRECTED LEARNING DYNAMICS IN DEEP LINEAR NETWORKS | Sep 25, 2019 | Second-order methods | —Unverified | 0 |
| Quasi-Newton Optimization Methods For Deep Learning Applications | Sep 4, 2019 | Deep LearningDeep Reinforcement Learning | —Unverified | 0 |
| Practical Newton-Type Distributed Learning using Gradient Based Approximations | Jul 22, 2019 | Second-order methodsVocal Bursts Type Prediction | —Unverified | 0 |
| Meta-descent for Online, Continual Prediction | Jul 17, 2019 | PredictionSecond-order methods | —Unverified | 0 |
| SGD momentum optimizer with step estimation by online parabola model | Jul 16, 2019 | Second-order methods | CodeCode Available | 0 |
| Limitations of the Empirical Fisher Approximation for Natural Gradient Descent | May 29, 2019 | Second-order methods | CodeCode Available | 0 |
| Gram-Gauss-Newton Method: Learning Overparameterized Neural Networks for Regression Problems | May 28, 2019 | regressionSecond-order methods | —Unverified | 0 |
| LIBS2ML: A Library for Scalable Second Order Machine Learning Algorithms | Apr 20, 2019 | BIG-bench Machine LearningSecond-order methods | CodeCode Available | 0 |
| Improving SGD convergence by online linear regression of gradients in multiple statistically relevant directions | Jan 31, 2019 | regressionSecond-order methods | CodeCode Available | 0 |
| Stochastic Trust Region Inexact Newton Method for Large-scale Machine Learning | Dec 26, 2018 | BIG-bench Machine LearningSecond-order methods | CodeCode Available | 0 |
| Bilinear Parameterization For Differentiable Rank-Regularization | Nov 27, 2018 | Second-order methods | —Unverified | 0 |
| Deep Reinforcement Learning via L-BFGS Optimization | Nov 6, 2018 | Atari GamesDeep Reinforcement Learning | —Unverified | 0 |
| Large batch size training of neural networks with adversarial training and second-order information | Oct 2, 2018 | Second-order methods | CodeCode Available | 0 |
| Stochastic Second-order Methods for Non-convex Optimization with Inexact Hessian and Gradient | Sep 26, 2018 | Second-order methods | —Unverified | 0 |
| A Distributed Second-Order Algorithm You Can Trust | Jun 20, 2018 | Distributed OptimizationSecond-order methods | —Unverified | 0 |
| Online Second Order Methods for Non-Convex Stochastic Optimizations | Mar 26, 2018 | Second-order methods | CodeCode Available | 0 |
| GPU Accelerated Sub-Sampled Newton's Method | Feb 26, 2018 | GPUSecond-order methods | —Unverified | 0 |
| The Many Faces of Exponential Weights in Online Learning | Feb 21, 2018 | Second-order methods | —Unverified | 0 |
| A comparison of second-order methods for deep convolutional neural networks | Jan 1, 2018 | Second-order methods | —Unverified | 0 |