Randy Ardywibowo

Ph.D.

Biography

My current research interests is on reinforcement learning, language agents & reasoning, sampling techniques, and contextual bandits. I am currently building Machine Learning algorithms @ Apple Inc.

I received my doctorate in Electrical Engineering at Texas A&M University under the supervision of Dr. Xiaoning Qian. During my studies, I researched uncertainty quantification in machine learning, with applications to time-series prediction, computer vision, energy-efficient ML, anomaly detection, continual learning, deep model compression, and healthcare monitoring.

Download my resumé.

Interests

Reinforcement Learning
Language Agents & Reasoning
Sampling Techniques

Education

Electrical Engineering, Ph.D., 2022
Texas A&M University

Research Statement

Randy Ardywibowo

Dec 11, 2024 3 min read

Scaling Supervision with Intrinsic Rewards

“Intrinsic rewards are the self-supervised pretraining stage for reinforcement learning agents.” One of the most critical challenges in training AI systems today is finding scalable supervision signals. As models grow in complexity and their applications extend into increasingly nuanced domains, providing supervision to lead them towards performing well on a task becomes more difficult.

Experience

Machine Learning Engineer

Apple

Aug 2022 – Present Cupertino, California

Reinforcement Learning, Language Agents, Information Retrieval, Contextual Bandits

Graduate Researcher

Texas A&M University

Sep 2017 – Aug 2022 College Station, Texas

Variational Inference, Continual Learning, Uncertainty Quantification, Outlier Detection, Model Robustness

Intern

Qualcomm

May 2020 – Aug 2020 San Diego, California

Computer Vision, DNN Model Compression.

Research Scientist

University of Washington

May 2018 – Sep 2018 Seattle, Washington

Computer Vision, Skin Disease, Medicine.

Recent Publications

Randy Ardywibowo, Rakesh Sunki, Lucy Kuo, Sankalp Nayak (2024). BayesCNS: A Unified Bayesian Approach to Address Cold Start and Non-Stationarity in Search Systems at Scale. AAAI 2025.

PDF Cite

Randy Ardywibowo, Zepeng Huo, Zhangyang Wang, Bobak Mortazavi, Shuai Huang, Xiaoning Qian (2022). VariGrow: Variational Architecture Growing for Task-Agnostic Continual Learning based on Bayesian Novelty. ICML 2022.

PDF Cite Code

Randy Ardywibowo, Shahin Boluki, Zhangyang Wang, Bobak Mortazavi, Shuai Huang, Xiaoning Qian (2022). VFDS: Variational Foresight Dynamic Selection in Bayesian Neural Networks. AISTATS 2022.

PDF Cite Code

Randy Ardywibowo, Venkata Ravi Kiran Dayana, Hau Hwang (2022). Dynamic Quantization for Energy Efficient Deep Learning. U.S. Patent App..

PDF Cite

Randy Ardywibowo, Shahin Boluki, Xinyu Gong, Zhangyang Wang, Xiaoning Qian (2020). NADS: Neural Architecture Distribution Search for Uncertainty Awareness. ICML 2020.

PDF Cite Code

Shahin Boluki, Randy Ardywibowo, Siamak Zamani Dadaneh, Mingyuan Zhou, Xiaoning Qian (2020). Learnable Bernoulli Dropout for Bayesian Deep Learning. AISTATS 2020.

PDF Cite Code

Ziyu Jiang, Randy Ardywibowo, Aven Samereh, Heather L. Evans, William B. Lober, Xiangyu Chang, Xiaoning Qian, Zhangyang Wang, Shuai Huang (2019). A Roadmap for Automatic Surgical Site Infection Detection and Evaluation Using User-Generated Incision Images. Surgical Infections 2019.

PDF Cite DOI

Randy Ardywibowo, Guang Zhao, Zhangyang Wang, Bobak Mortazavi, Shuai Huang, Xiaoning Qian (2019). Adaptive Activity Monitoring with Uncertainty Quantification in Switching Gaussian Process Models. AISTATS 2019.

PDF Cite Code

See all publications