There are 3 repositories under non-convex-optimization topic.
skscope: Sparse-Constrained OPtimization via itErative-solvers
A curated list of papers of interesting empirical study and insight on deep learning. Continually updating...
MoveIt kinematics_base plugin based on particle optimization & GA
A generic optimization method for any integer programming problem
Awesome list for Neural Network Optimization methods.
Safe Pontryagin Differentiable Programming (Safe PDP) is a new theoretical and algorithmic safe differentiable framework to solve a broad class of safety-critical learning and control tasks.
Riemannian stochastic optimization algorithms: Version 1.0.3
Visualization of various deep learning optimization algorithms using PyTorch automatic differentiation and optimizers.
Simulation code for "Achievable Rate Maximization for Underlay Spectrum Sharing MIMO System with Intelligent Reflecting Surface," by V. Kumar, M. F. Flanagan, R. Zhang, and L. -N. Tran, IEEE Wireless Communications Letters, 2022, doi: 10.1109/LWC.2022.3180988.
Codes for the paper "Deep Neural Networks with Multi-Branch Architectures Are Less Non-Convex"
Numerical illustration of a novel analysis framework for consensus-based optimization (CBO) and numerical experiments demonstrating the practicability of the method
Simulation code for "On the Secrecy Rate under Statistical QoS Provisioning for RIS-assisted MISO Wiretap Channel," by V. Kumar, M. F. Flanagan, D. W. Kwan Ng, and L. -N. Tran, IEEE Global Communications Conference (GLOBECOM), 2021, pp. 1-6, doi: 10.1109/GLOBECOM46510.2021.9685957.
Pyoneer is a Python 3 package for the continuous recovery of non-bandlimited periodic signals with finite rates of innovation (e.g. Dirac streams) from generalised measurements.
New Matrix Factorization Algorithms based on Bregman Proximal Gradient: BPG-MF, CoCaIn BPG-MF, BPG-MF-WB
an R package implementing the grid search optimization algorithm with a zoom
Semi-blind deconvolution for fMRI (BOLD signal)
Fast Inertial Algorithm for Phase Retrieval
Sequential Convex Optimization for TAMP problems with multiple backend solvers!
Information network edge representation learning using edge-to-vertex dual graphs (a.k.a line graph). In addition to that, an optimisation problem is solved efficiently to generate the edge embeddings.
In compressed decentralized optimization settings, there are benefits to having multiple gossip steps between subsequent gradient iterations, even when the cost of doing so is appropriately accounted for e.g. by means of reducing the precision of compressed information.
Numerical analysis of Particle Swarm Optimization (PSO) and numerical experiments demonstrating the practicability of the method
CoCaIn BPG escapes Spurious Stationary Points
Low-dose cryo electron ptychography via non-convex Bayesian optimization
This repository contains the work done as part of my B.Tech Project
A Balanced Teaching Learning Based Optimization Algorithm. This project was developed under supervision of Dr. Keyvan RahimiZadeh and in collabotion with Prof. R. Venkata Rao.
My undergraduate thesis at THU
Adaptive Moving Average as an Unsupervised Learning Algorithm
Contains code for RL and NES scheduling algorithms to optimize a flood control problem in a water dam
Discussion of advantages and disadvantages of AdaHessian, a state-of-the-art Second Order Methods over First Order Methods on a Non-Convex Optimization Problem (digits classification on MNIST database using ResNet18). - @ EPFL
Classification-Techniques-For-Fraud-Detection
A cutting-edge implementation of Particle Swarm Optimization (PSO) tailored for navigating and optimizing complex non-convex functions. This project encapsulates an advanced algorithmic approach, leveraging swarm intelligence to efficiently converge on global minima in multimodal landscapes.
Tutorials on optimizers for deep neural networks