Gradient flows in dataset space
AssigneeMicrosoft Technology Licensing, LLC
InventorsDavid Alvarez-Melis, Nicolo Fusi
Life of this patent
Estimating the term…
Abstract
Generally discussed herein are devices, systems, and methods for machine learning (ML) by flowing a dataset towards a target dataset. A method can include receiving a request to operate on a first dataset including first feature, label pairs, identifying a second dataset from multiple datasets, the second dataset including second feature, label pairs, determining a distance between the first feature, label and the second feature, label pairs, and flowing the first dataset using a dataset objective that operates based on the determined distance to generate an optimized dataset.
Claims20
A computer-implemented method for machine learning (ML) by flowing a dataset towards a target dataset, the method comprising:
- receiving a request to operate on a first dataset including first feature, label pairs;
- identifying or receiving a second dataset, the second dataset including second feature, label pairs;
- determining a distance between the first feature, label and the second feature, label pairs;
- and
- flowing the first dataset using a dataset objective that operates based on the determined distance to generate an optimized dataset.
A non-transitory machine-readable medium including instructions that, when executed by a machine, cause the machine to perform operations for machine learning (ML) by flowing a dataset towards a target dataset, the operations comprising:
- receiving a request to operate on a first dataset including first feature, label pairs;
- identifying or receiving a second dataset, the second dataset including second feature, label pairs;
- determining a distance between the first feature, label and the second feature, label pairs;
- and
- flowing the first dataset using a dataset objective that operates based on the determined distance to generate an optimized dataset.
A system for supervised machine learning (ML) that flows a dataset towards a target dataset, the system comprising:
- a memory including instructions stored thereon;
- processing circuitry coupled to the memory, the instructions, when executed by the processing circuitry configure the processing circuitry to:
- receive a request to operate on a first dataset including first feature, label pairs;
- identify or receive a second dataset from multiple datasets, the second dataset including second feature, label pairs;
- determine a distance between the first feature, label pairs and the second feature, label pairs;
- and
- flowing the first dataset using a dataset objective that operates based on the determined distance to generate an optimized dataset.
Dependencies are inferred from the claim text.