Results 11 to 20 of about 632,931 (308)

Deci-AI/super-gradients: 3.1.2

open access: yes, 2023
What's Changed Hotfix/sg 000 fix doc typo rf100 by @Louis-Dupont in https://github.com/Deci-AI/super-gradients/pull/897 Fixed false-positive warning message by @BloodAxe in https://github.com/Deci-AI/super-gradients/pull/886 Update deprecate ...
Borys Tymchenko   +28 more
core   +3 more sources

Gradient Convergence in Gradient methods with Errors [PDF]

open access: yesSIAM Journal on Optimization, 2000
Summary: We consider the gradient method \(x_{t+1}=x_t+\gamma_t(s_t+w_t)\), where \(s_t\) is a descent direction of a function \(f:{\mathfrak R}^n\to{\mathfrak R}\) and \(w_t\) is a deterministic or stochastic error. We assume that \(\nabla f\) is Lipschitz continuous, that the stepsize \(\gamma_t\) diminishes to 0, and that \(s_t\) and \(w_t\) satisfy
Dimitri P. Bertsekas, John N. Tsitsiklis
openaire   +2 more sources

Gradient Correction beyond Gradient Descent

open access: yesCoRR, 2022
The great success neural networks have achieved is inseparable from the application of gradient-descent (GD) algorithms. Based on GD, many variant algorithms have emerged to improve the GD optimization process. The gradient for back-propagation is apparently the most crucial aspect for the training of a neural network.
Li, Zefan   +4 more
openaire   +3 more sources

Is the Policy Gradient a Gradient?

open access: yesInternational Joint Conference on Autonomous Agents and Multiagent Systems, 2020
The policy gradient theorem describes the gradient of the expected discounted return with respect to an agent's policy parameters. However, most policy gradient methods drop the discount factor from the state distribution and therefore do not optimize the discounted objective. What do they optimize instead?
Chris Nota, Philip S. Thomas
openaire   +3 more sources

Gradients

open access: yes, 2022
Group/individual functional connectivity gradients.
Ana Manea (12101003)
core   +1 more source

Stochastic Gradient Langevin with Delayed Gradients

open access: yesCoRR, 2020
Stochastic Gradient Langevin Dynamics (SGLD) ensures strong guarantees with regards to convergence in measure for sampling log-concave posterior distributions by adding noise to stochastic gradient iterates. Given the size of many practical problems, parallelizing across several asynchronously running processors is a popular strategy for reducing the ...
Vyacheslav Kungurtsev   +2 more
openaire   +2 more sources

Deci-AI/super-gradients: 3.1.0

open access: yes, 2023
What's Changed Hotfix/sg 000 fix predict show by @Louis-Dupont in https://github.com/Deci-AI/super-gradients/pull/846 Feature/sg 814 support yoloformat loader by @Louis-Dupont in https://github.com/Deci-AI/super-gradients/pull/847 Feature/sg 812 return ...
Borys Tymchenko   +20 more
core   +1 more source

Deci-AI/super-gradients: 3.1.3

open access: yes, 2023
What's Changed Hotfix/alg 1470 drop boxes padding by @yurkovak in https://github.com/Deci-AI/super-gradients/pull/1107 replace image by @ofrimasad in https://github.com/Deci-AI/super-gradients/pull/1149 Update README.md by @ofrimasad in https://github ...
Borys Tymchenko   +29 more
core   +1 more source

Deci-AI/super-gradients: 3.1.1

open access: yes, 2023
What's Changed fix documentation after version by @ofrimasad in https://github.com/Deci-AI/super-gradients/pull/879 Update links to notebooks and to Discord community by @BloodAxe in https://github.com/Deci-AI/super-gradients/pull/881 Fix image with ...
Borys Tymchenko   +23 more
core   +1 more source

Analytic Gradients for PR-MP2 (Scheme I) [PDF]

open access: yes, 2023
Analytic gradients for the partially renormalized second-order Moller-Plesset perturbation theory (Scheme I) are derived using the Lagrangian method.
Yoshio, Nishimoto
core   +1 more source

Home - About - Disclaimer - Privacy