Mohsen Ghassemi

Title: Mohsen Ghassemi: Innovator in Differentially Private Learning

Introduction

Mohsen Ghassemi is an accomplished inventor based in Jersey City, NJ (US). He has made significant contributions to the field of data privacy through his innovative patent. His work focuses on preserving individual privacy while modeling event sequence data, which is increasingly important in today's data-driven world.

Latest Patents

Ghassemi holds a patent titled "Method and system for differentially private learning of Hawkes processes." This patent presents a method for preserving privacy in modeling event sequence data. The method involves receiving information about a sequence of events and modeling it using a Hawkes process. This process includes an intensity that consists of an exogenous base intensity rate and an indigenous component with an excitation rate and a decay rate. The method analyzes the received information and determines estimated values for the intensity rates, ensuring that the accuracy of these estimates corresponds to the observation time of the event sequence. To maintain differential privacy, noise is added to the event sequence, which helps protect the privacy of individuals associated with the events. The cost of achieving differential privacy is expressed as an additional length of observation time required for accurate estimates. Ghassemi's patent represents a significant advancement in the field of privacy-preserving data analysis.

Career Highlights

Mohsen Ghassemi is currently employed at JPMorgan Chase Bank, N.A., where he applies his expertise in data privacy and modeling. His work at the bank allows him to contribute to innovative solutions that address the challenges of data privacy in financial services. Ghassemi's background and experience in this field have positioned him as a valuable asset to his organization.

Collaborations

Ghassemi collaborates with talented professionals in his field, including Eleonora Kreacic and Niccolo Dalmasso. These collaborations enhance the innovative work being done in the realm of data privacy and modeling.

Conclusion

Mohsen Ghassemi is a notable inventor whose work in differentially private learning has the potential to transform how event sequence data is modeled while preserving individual privacy. His contributions are essential in the ongoing effort to balance data utility and privacy in various applications.