Papers with Code 아카이브
Second-order methods
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Use second-order statistics to process data.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Learning Rates as a Function of Batch Size: A Random Matrix Theory Approach to Neural Network Training
Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective Bayesian Optimization
SONIA: A Symmetric Blockwise Truncated Optimization Algorithm
Asymptotic Analysis of Conditioned Stochastic Gradient Descent
On the Promise of the Stochastic Generalized Gauss-Newton Method for Training DNNs
ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning
MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulation
Critical Point-Finding Methods Reveal Gradient-Flat Regions of Deep Network Losses
Stochastic Subspace Cubic Newton Method
DDPNOpt: Differential Dynamic Programming Neural Optimizer
Low Rank Saddle Free Newton: A Scalable Method for Stochastic Nonconvex Optimization
Newtonian Monte Carlo: single-site MCMC meets second-order gradient methods
Stochastic Newton and Cubic Newton Methods with Simple Local Linear-Quadratic Rates
Hierarchical model-based policy optimization: from actions to action sequences and back
Implementation of a modified Nesterov's Accelerated quasi-Newton Method on Tensorflow
Fast and Furious Convergence: Stochastic Second Order Methods under Interpolation
Quasi-Newton Optimization Methods For Deep Learning Applications
Practical Newton-Type Distributed Learning using Gradient Based Approximations
Meta-descent for Online, Continual Prediction
SGD momentum optimizer with step estimation by online parabola model
Limitations of the Empirical Fisher Approximation for Natural Gradient Descent
Gram-Gauss-Newton Method: Learning Overparameterized Neural Networks for Regression Problems
LIBS2ML: A Library for Scalable Second Order Machine Learning Algorithms
Improving SGD convergence by online linear regression of gradients in multiple statistically relevant directions
Stochastic Trust Region Inexact Newton Method for Large-scale Machine Learning
Bilinear Parameterization For Differentiable Rank-Regularization
Deep Reinforcement Learning via L-BFGS Optimization
Large batch size training of neural networks with adversarial training and second-order information
Stochastic Second-order Methods for Non-convex Optimization with Inexact Hessian and Gradient
A Distributed Second-Order Algorithm You Can Trust
Online Second Order Methods for Non-Convex Stochastic Optimizations
GPU Accelerated Sub-Sampled Newton's Method
The Many Faces of Exponential Weights in Online Learning
Block-diagonal Hessian-free Optimization for Training Neural Networks
Nesterov's Acceleration For Approximate Newton
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.