Iterative technique to identify global minimum in a dataset

Patent metadata

Field	Value
Publication number	US-2026099758-A1
Application number	US-202418906974-A
Country	US
Kind code	A1
Filing date	Oct 4, 2024
Priority date	Oct 4, 2024
Publication date	Apr 9, 2026
Grant date	—

Abstract

An application server may receive a request to train the machine learning model on a dataset, and may generate a first set of randomized solutions based on inputting one or more of a set of model parameters into the machine learning model, where the first set of randomized solutions correspond to a set of outputs generated by the machine learning model and spans at least a subset of a set of local minimums. The application server may then select a first solution from the first set of randomized solutions and generate a second set of randomized solutions based on the first solution and inputting one or more of the set of model parameters into the machine learning model. The application server may then determine that the second set of randomized solutions includes a global minimum of the dataset based on the second set of randomized solutions satisfying a threshold.

First claim

What is claimed is:

1 . A method for data processing, comprising:
receiving, from a user and at an interface for accessing a machine learning model, a request to train the machine learning model on a dataset by iteratively inputting a set of model parameters into the machine learning model to minimize a loss function associated with the dataset, wherein the dataset comprises a plurality of local minimums; generating a first set of randomized solutions based at least in part on inputting one or more of the set of model parameters into the machine learning model, wherein the first set of randomized solutions corresponds to a set of outputs generated by the machine learning model upon inputting the set of model parameters, and wherein the first set of randomized solutions spans at least a subset of the plurality of local minimums; selecting a first solution from the first set of randomized solutions, the first solution having a minimum loss value of a first set of loss values corresponding to the first set of randomized solutions, the first solution corresponding to the at least one local minimum of the plurality of local minimums of the dataset; generating a second set of randomized solutions based at least in part on the first solution and inputting one or more of the set of model parameters into the machine learning model; determining that the second set of randomized solutions comprises a global minimum of the dataset based at least in part on the second set of randomized solutions satisfying a threshold; and providing for display, via the interface, an indication of completion of training of the machine learning model based at least in part on the second set of randomized solutions comprising the global minimum of the dataset.

2 . The method of claim 1 , wherein determining that the second set of randomized solutions comprises the global minimum of the dataset further comprises:
iteratively generating a plurality of randomized solutions for a first quantity iterations prior to generating the second set of randomized solutions; and determining that the second set of randomized solutions comprises the global minimum of the dataset based at least in part on the first quantity of iterations satisfying a threshold quantity of iterations.

3 . The method of claim 1 , further comprising:
calculating an average change between the first set of randomized solutions and the second set of randomized solutions, wherein determining that the second set of randomized solutions comprises the global minimum of the dataset is based at least in part on the average change being less than a threshold level.

4 . The method of claim 1 , further comprising:
generating the first set of loss values corresponding to the first set of randomized solutions based at least in part on computing a loss value for each randomized solution of the first set of randomized solutions using the loss function associated with the dataset.

5 . The method of claim 1 , further comprising:
generating a set of updated model parameters for inputting into the machine learning model based at least in part on adding one or more deviations to the set of model parameters, wherein generating the second set of randomized solutions is based at least in part on the set of updated model parameters.

6 . The method of claim 1 , wherein the second set of randomized solutions is generated within a threshold distance of a search space associated with the first solution.

7 . The method of claim 1 , wherein the set of model parameters is based at least in part on a dimensionality of a search space associated with the machine learning model.

8 . The method of claim 1 , wherein the machine learning model comprises a gradient-based machine learning model.

9 . An apparatus for data processing, comprising:
one or more memories storing processor-executable code; and one or more processors coupled with the one or more memories and individually or collectively operable to execute the code to cause the apparatus to:
receive, from a user and at an interface for accessing a machine learning model, a request to train the machine learning model on a dataset by iteratively inputting a set of model parameters into the machine learning model to minimize a loss function associated with the dataset, wherein the dataset comprises a plurality of local minimums;
generate a first set of randomized solutions based at least in part on inputting one or more of the set of model parameters into the machine learning model, wherein the first set of randomized solutions corresponds to a set of outputs generated by the machine learning model upon inputting the set of model parameters, and wherein the first set of randomized solutions spans at least a subset of the plurality of local minimums;
select a first solution from the first set of randomized solutions, the first solution having a minimum loss value of a first set of loss values corresponding to the first set of randomized solutions, the first solution corresponding to the at least one local minimum of the plurality of local minimums of the dataset;
generate a second set of randomized solutions based at least in part on the first solution and inputting one or more of the set of model parameters into the machine learning model;
determine that the second set of randomized solutions comprises a global minimum of the dataset based at least in part on the second set of randomized solutions satisfying a threshold; and
provide for display, via the interface, an indication of completion of training of the machine learning model based at least in part on the second set of randomized solutions comprising the global minimum of the dataset.

10 . The apparatus of claim 9 , wherein, to determine that the second set of randomized solutions comprises the global minimum of the dataset, the one or more processors are individually or collectively further operable to execute the code to cause the apparatus to:
iteratively generate a plurality of randomized solutions for a first quantity iterations prior to generating the second set of randomized solutions; and determine that the second set of randomized solutions comprises the global minimum of the dataset based at least in part on the first quantity of iterations satisfying a threshold quantity of iterations.

11 . The apparatus of claim 9 , wherein the one or more processors are individually or collectively further operable to execute the code to cause the apparatus to:
calculate an average change between the first set of randomized solutions and the second set of randomized solutions, wherein determining that the second set of randomized solutions comprises the global minimum of the dataset is based at least in part on the average change being less than a threshold level.

12 . The apparatus of claim 9 , wherein the one or more processors are individually or collectively further operable to execute the code to cause the apparatus to:
generate the first set of loss values corresponding to the first set of randomized solutions based at least in part on computing a loss value for each randomized solution of the first set of randomized solutions using the loss function associated with the dataset.

13 . The apparatus of claim 9 , wherein the one or more processors are individually or collectively further operable to execute the code to cause the apparatus to:
generate a set of updated model parameters for inputting into the machine learning model based at least in part on adding one or more deviations to the set of model parameters, wherein generating the second set of randomized solutions is based at least in part on th

Assignees

• Salesforce Inc

Inventors

• Padhi Bikramaditya
• Kothandaraman Ramprasadh

Classifications

• G06N20/00 Primary

  Machine learning · CPC title