CV

Basics

Name Aman Malali
Label MS/PhD Student
Email amalali@umass.edu
Url https://amanmalali.github.io/
Summary PhD student at UMass Amherst working in the field of MLOps, focusing on model maintenance and retraining

Work

  • 09.01 - Present
    Data systems Research for Exploration, Analytics, and Modeling Lab (DREAM Lab)
    University of Massachusetts Amherst
    Predictive machine learning (ML) model maintenance
    • Currently working on methods to predict model performance without ground truth by utilizing custom ensemble models and uncertainty measures.
    • Creating predictive retraining strategies to retrain models with minimal downtime and improved predictive performance on drifting data.
  • 06.17 - 09.06
    PhD Research Intern
    Dolby Advanced Technology Group (ATG)
    Extended and improved predictive ML model maintenance
    • Developed a dynamic temperature scaling method for machine learning models that calibrates logits based on input features, improving uncertainty estimation and prediction reliability
    • Expanded predictive model maintenance by incorporating granular loss levels and adaptive loss bounds to optimize retraining decisions, while experimenting with extensions to address concept drift.

Education

  • 09.01 - present

    Amherst, MA, USA

    M.S/PhD Student
    University of Massachusetts Amherst
    Computer Science
    • COMPSCI 683: Artificial Intelligence
    • COMPSCI 645: Database Design and Implementation
    • COMPSCI 611: Advanced Algorithms
    • COMPSCI 682: Neural Networks

Publications

Languages

English
Native speaker
Hindi
Native speaker
Kannada
Fluent