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.
Near out-of-distribution detection for low-resolution radar micro-Doppler signatures
A Novel Fast Exact Subproblem Solver for Stochastic Quasi-Newton Cubic Regularized Optimization
Accelerating Stochastic Probabilistic Inference
Amortized Proximal Optimization
Generalized Optimistic Methods for Convex-Concave Saddle Point Problems
A Mini-Block Fisher Method for Deep Neural Networks
Communication-Efficient Stochastic Zeroth-Order Optimization for Federated Learning
Accelerated Projected Gradient Method for the Optimization of Cell-Free Massive MIMO Downlink
SCORE: Approximating Curvature Information under Self-Concordant Regularization
Newton methods based convolution neural networks using parallel processing
Basis Matters: Better Communication-Efficient Second Order Methods for Federated Learning
Provable Regret Bounds for Deep Online Learning and Control
KKT Conditions, First-Order and Second-Order Optimization, and Distributed Optimization: Tutorial and Survey
Second-Order Neural ODE Optimizer
Nonlinear matrix recovery using optimization on the Grassmann manifold
Doubly Adaptive Scaled Algorithm for Machine Learning Using Second-Order Information
Structured second-order methods via natural gradient descent
M-FAC: Efficient Matrix-Free Approximations of Second-Order Information
LocoProp: Enhancing BackProp via Local Loss Optimization
Tensor Normal Training for Deep Learning Models
FedNL: Making Newton-Type Methods Applicable to Federated Learning
Exact Stochastic Second Order Deep Learning
Quasi-Newton Quasi-Monte Carlo for variational Bayes
Research of Damped Newton Stochastic Gradient Descent Method for Neural Network Training
A Distributed Optimisation Framework Combining Natural Gradient with Hessian-Free for Discriminative Sequence Training
Learning-Augmented Sketches for Hessians
Distributed Second Order Methods with Fast Rates and Compressed Communication
Kronecker-factored Quasi-Newton Methods for Deep Learning
Noise and Fluctuation of Finite Learning Rate Stochastic Gradient Descent
Second-order Neural Network Training Using Complex-step Directional Derivative
Utility Maximization for Large-Scale Cell-Free Massive MIMO Downlink
Debiasing Distributed Second Order Optimization with Surrogate Sketching and Scaled Regularization
Second-Order Information in Non-Convex Stochastic Optimization: Power and Limitations
When Does Preconditioning Help or Hurt Generalization?
Enhance Curvature Information by Structured Stochastic Quasi-Newton Methods
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.