# US 2025/0094531 A1 · Information processing apparatus

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0094531 A1
- Document ID: US20250094531A1
- Status: Published application
- Kind: A1
- Application number: 18/368,802
- Filed: 2023-09-15
- Published: 2025-03-20
- Earliest claimed: 2023-09-15
- Assignees: Hitachi, Ltd.
- Applicants: HITACHI, Ltd.
- Inventors: Takuya OKUYAMA
- Web page: https://patentgrep.com/patent/US20250094531A1

## CPC

- G06F 17/16: Matrix or vector computation {, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization (matrix transposition G06F7/78)}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Aspects of the present disclosure can involve systems and methods for accelerating a process to search for optimal solutions for interaction models, the process involving iterative matrix multiplication between a first matrix and a second matrix, which include replacing the first matrix with a first approximate matrix and the second matrix with a second approximate matrix through adding a first set of constant values to the first matrix and a second set of constant values to the second matrix; executing a Monte Carlo Approximate Matrix Multiplication between the first approximate matrix and the second approximate matrix to generate an approximate matrix product; executing the process to search for the optimal solutions based on the approximate matrix product according to the interaction models; and providing the optimal solutions found from the process.

## Claims

### Claim 1

A method for accelerating a process to search for optimal solutions for interaction models, the process involving iterative matrix multiplication between a first matrix and a second matrix, the method comprising:
replacing the first matrix with a first approximate matrix and the second matrix with a second approximate matrix through adding a first set of constant values to the first matrix and a second set of constant values to the second matrix;
executing a Monte Carlo Approximate Matrix Multiplication between the first approximate matrix and the second approximate matrix to generate an approximate matrix product;
executing the process to search for the optimal solutions based on the approximate matrix product according to the interaction models; and
providing the optimal solutions found from the process.

### Claim 2 (depends on 1)

The method of claim 1, wherein the method is executed using parallel processing on Graphics Processor Units (GPUs) or Field Programmable Gate Arrays (FPGAs).

### Claim 3 (depends on 1)

The method of claim 1, wherein the process to search for the optimal solutions is a Complementary Metal Oxide Semiconductor (CMOS) annealing process and the interaction models comprises Ising model.

### Claim 4 (depends on 1)

The method of claim 1, wherein the process is a neural network computation.

### Claim 5 (depends on 1)

The method of claim 1, wherein the process is an eigenvalue computation.

### Claim 6 (depends on 1)

The method of claim 1, wherein the executing the Monte Carlo Approximate Matrix Multiplication comprises:
determining a first vector based on the first set of constant values and a second vector based on the second set of constant values;
generating the approximate matrix product from the Monte Carlo Approximate Matrix Multiplication from a sum of: a matrix product result of the Monte Carlo Approximate Matrix multiplication, a vector product of the second vector with the first approximate matrix, a vector product of the second approximate matrix with the first vector, and an inner product involving the first set of constant values and the second set of constant values.

### Claim 7 (depends on 1)

The method of claim 1, wherein the first set of constant values and the second set of constant values are selected such that matrix multiplication result of the first matrix and the second matrix is equivalent to a sum of a matrix multiplication result of the first approximate matrix and the second approximate matrix, one or more vector multiplication operations involving the first approximate matrix and the second approximate matrix, and one or more inner product operations involving the first set of constant values and the second set of constant values.

### Claim 8

An information processing device configured to accelerate a process to search for optimal solutions for interaction models, the process involving iterative matrix multiplication between a first matrix and a second matrix, the information processing device comprising:
a processor, configured to control one or more calculation devices to execute, using parallel processing:
replacing the first matrix with a first approximate matrix and the second matrix with a second approximate matrix through adding a first set of constant values to the first matrix and a second set of constant values to the second matrix;
executing a Monte Carlo Approximate Matrix Multiplication between the first approximate matrix and the second approximate matrix to generate an approximate matrix product;
executing the process to search for the optimal solutions based on the approximate matrix product according to the interaction models; and
providing the optimal solutions found from the process.

### Claim 9 (depends on 8)

The information processing device of claim 8, wherein the one or more calculation devices comprises Graphics Processor Units (GPUs) or Field Programmable Gate Arrays (FPGAs).

### Claim 10 (depends on 8)

The information processing device of claim 8, wherein the process to search for the optimal solutions is a Complementary Metal Oxide Semiconductor (CMOS) annealing process and the interaction models comprises Ising model.

### Claim 11 (depends on 8)

The information processing device of claim 8, wherein the process is a neural network computation.

### Claim 12 (depends on 8)

The information processing device of claim 8, wherein the process is an eigenvalue computation.

### Claim 13 (depends on 8)

The information processing device of claim 8, wherein the processor is configured to control the one or more calculation devices to execute, using parallel processing, the Monte Carlo Approximate Matrix Multiplication by:
determining a first vector based on the first set of constant values and a second vector based on the second set of constant values;
generating the approximate matrix product from the Monte Carlo Approximate Matrix Multiplication from a sum of: a matrix product result of the Monte Carlo Approximate Matrix multiplication, a vector product of the second vector with the first approximate matrix, a vector product of the second approximate matrix with the first vector, and an inner product involving the first set of constant values and the second set of constant values.

### Claim 14 (depends on 8)

The information processing device of claim 8, wherein the first set of constant values and the second set of constant values are selected such that matrix multiplication result of the first matrix and the second matrix is equivalent to a sum of a matrix multiplication result of the first approximate matrix and the second approximate matrix, one or more vector multiplication operations involving the first approximate matrix and the second approximate matrix, and one or more inner product operations involving the first set of constant values and the second set of constant values.

### Claim 15

A non-transitory computer readable medium, storing instructions for accelerating a process to search for optimal solutions for interaction models, the process involving iterative matrix multiplication between a first matrix and a second matrix, the instructions comprising:
replacing the first matrix with a first approximate matrix and the second matrix with a second approximate matrix through adding a first set of constant values to the first matrix and a second set of constant values to the second matrix;
executing a Monte Carlo Approximate Matrix Multiplication between the first approximate matrix and the second approximate matrix to generate an approximate matrix product;
executing the process to search for the optimal solutions based on the approximate matrix product according to the interaction models; and
providing the optimal solutions found from the process.
