18049183. COMBINATORIAL OPTIMIZATION PROBLEM SIZE REDUCTION USING MACHINE LEARNING IN EDGE ENVIRONMENTS simplified abstract (Dell Products L.P.)
Contents
COMBINATORIAL OPTIMIZATION PROBLEM SIZE REDUCTION USING MACHINE LEARNING IN EDGE ENVIRONMENTS
Organization Name
Inventor(s)
[[:Category:Miguel Paredes Qui�ones of Campinas (BR)|Miguel Paredes Qui�ones of Campinas (BR)]][[Category:Miguel Paredes Qui�ones of Campinas (BR)]]
Ítalo Gomes Santana of Rio de Janeiro (BR)
Vinicius Michel Gottin of Rio de Janeiro (BR)
COMBINATORIAL OPTIMIZATION PROBLEM SIZE REDUCTION USING MACHINE LEARNING IN EDGE ENVIRONMENTS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18049183 titled 'COMBINATORIAL OPTIMIZATION PROBLEM SIZE REDUCTION USING MACHINE LEARNING IN EDGE ENVIRONMENTS
Simplified Explanation: The patent application discloses a method to reduce the size of combinatorial optimization problems by generating empirical data, training a model to output encoded distributions, and sampling inputs from these distributions to solve smaller optimization problems.
- Machine learning model trained to output encoded distributions
- Sampling inputs from encoded distributions to reduce problem size
- Solving reduced size optimization problems at edge nodes
- Feasible solutions used for operational purposes
Key Features and Innovation:
- Generation of empirical data for relevant input features
- Training a model to output encoded distributions
- Sampling inputs from encoded distributions
- Solving smaller combinatorial optimization problems at edge nodes
Potential Applications: This technology can be applied in various industries such as logistics, supply chain management, telecommunications, and network optimization.
Problems Solved: This technology addresses the challenge of reducing the size of combinatorial optimization problems to make them more manageable and solvable at edge nodes.
Benefits:
- Improved efficiency in solving combinatorial optimization problems
- Reduction in computational resources required
- Feasible solutions for operational use
Commercial Applications: Reducing the size of combinatorial optimization problems can have significant commercial applications in industries that rely on optimization algorithms for decision-making processes.
Prior Art: There is no specific information provided on prior art related to this technology.
Frequently Updated Research: There is ongoing research in the field of machine learning and optimization algorithms that may impact the development and application of this technology.
Questions about the Technology: 1. How does this technology compare to traditional methods of solving combinatorial optimization problems? 2. What are the potential limitations of using machine learning models to reduce the size of optimization problems?
Original Abstract Submitted
Reducing the size of combinatorial optimization problems is disclosed. To reduce the size of a combinatorial optimization problem, empirical data is generated by generating results and empirical distributions of relevant input features. A model is trained to output encoded distributions may minimizing a loss between the empirical distributions and the machine learning generated distributions. Inputs are sampled from the encoded distribution, which results in a smaller size input and a smaller size combinatorial optimization problem. The reduced size combinatorial optimization problem can be solved at an edge node rather than a central node its solution can used for operational purposes as long as the solution is feasible.
