GitHub

SDPG: Self-Distilled Policy Gradient

SDPG is the main contribution. It extends GRPO with an exact per-token forward KL between the actor (without privileged context) and itself conditioned on privileged context c: ...
IEEE

New type of conjugate gradient algorithms for unconstrained optimization problems

Abstract: Two new formulaes of the main parameter β k of the conjugate gradient method are presented, which respectively can be seen as the modifications of method HS and PRP. In comparison with ...
GitHub

jlindbloom/gradient-projected-conjugate-gradient

This repository provides a Python implementation of the gradient projected conjugate gradient algorithm (GPCG) presented in [1] for solving bound-constrained quadratic programs of the form ...
The Conversation

Facebook’s algorithms fueled massive foreign propaganda campaigns during the 2020 election – here’s how algorithms can manipulate you

An internal Facebook report found that the social media platform’s algorithms – the rules its computers follow in deciding the content that you see – enabled disinformation campaigns based in Eastern ...
Scientific Research Publishing

Gradient-Based Iterative Algorithm for a Coupled Complex Conjugate and Transpose Matrix Equations ()

1 School of Management Science and Engineering, Anhui University of Finance & Economics, Bengbu, China. 2 College of Information & Network Engineering, Anhui Science & Technology University, Bengbu, ...
Scientific Research Publishing

Formulation of a Preconditioned Algorithm for the Conjugate Gradient Squared Method in Accordance with Its Logical Structure ()

1 Division of Science, School of Science and Engineering, Tokyo Denki University, Saitama, Japan. 2 Department of Physics and Mathematics, College of Science and Engineering, Aoyama Gakuin University, ...