Xueyu Mao

Title: Xueyu Mao: Innovator in Factorization Machines

Introduction

Xueyu Mao is a prominent inventor based in Austin, TX (US). He has made significant contributions to the field of machine learning, particularly in the optimization of factorization machines. His innovative approach has led to the development of techniques that enhance the training and updating of these models.

Latest Patents

Xueyu Mao holds a patent titled "Online training and update of factorization machines using alternating least squares optimization." This patent discloses techniques for training factorization machines (FMs) using a streaming mode alternating least squares (ALS) optimization. The methodology involves receiving a datapoint that includes a feature vector and an associated target value. The feature vector comprises user identification, subject matter identification, and context. The target value reflects the user's opinion regarding the subject matter. The method further applies an FM to the feature vector to generate an estimate of the target value and updates the parameters of the FM for training. This parameter update is based on the application of streaming mode ALS optimization to the datapoint, the estimate of the target value, and an updated summation of intermediate calculated terms from previously received datapoints.

Career Highlights

Xueyu Mao is currently employed at Adobe, Inc., where he continues to push the boundaries of innovation in machine learning. His work has garnered attention for its practical applications and effectiveness in real-world scenarios.

Collaborations

Xueyu collaborates with talented individuals such as Saayan Mitra and Viswanathan Swaminathan, contributing to a dynamic and innovative work environment.

Conclusion

Xueyu Mao's contributions to the field of factorization machines exemplify the impact of innovative thinking in technology. His patent and ongoing work at Adobe, Inc. highlight his role as a key player in advancing machine learning methodologies.