Welcome! I'm currently a PhD student at the Computer Science department of University of Toronto. My advisor is Gennady Pekhimenko . My research is motivated by developing ML tools and frameworks to benefit various end users, current including but not limited to the fields of neural architecture search and federated learning. I finished my Master of Science in Machine Learning at CMU, and I earned my Bachelor of Arts degree in Computer Science and History from Columbia University.

Select Publications

Self-supervised and Weakly Supervised Contrastive Learning for Frame-wise Action Representations
Minghao Chen*, Renbo Tu*, Chenxi Huang, Yuqi Lin, Boxi Wu, Deng Cai.
In submission to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022

NAS-Bench-360: Benchmarking Diverse Tasks for Neural Architecture Search
*Renbo Tu, *Nicholas Roberts, Mikhail Khodak, Junhong Shen, Frederic Sala, Ameet Talwalkar.
Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks, 2022
Website Code PDF

NAS-Bench-Suite-Zero: Accelerating Research on Zero Cost Proxies
Arjun Krishnakumar, Colin White, Arber Zela*, Renbo Tu*, Mahmoud Safari, Frank Hutter.
Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks, 2022
PDF Code

AutoML for Climate Change: A Call to Action
Renbo Tu, Nicholas Roberts, Vishak Prasad, Sibasis Nayak, Paarth Jain, Frederic Sala, Ganesh Ramakrishnan, Ameet Talwalkar, Willie Neiswanger, Colin White.
NeurIPS Workshop Tackling Climate Change with Machine Learning, 2022
PDF Code

Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing
Mikhail Khodak, Renbo Tu, Tian Li, Liam Li, Maria-Florina Balcan, Virginia Smith, Ameet Talwalkar.
Neural Information Processing Systems (NeurIPS), 2021
PDF Code

A Deeper Look at Zero-Cost Proxies for Lightweight NAS
Colin White, Mikhail Khodak, Renbo Tu, Shital Shah, Sébastien Bubeck, Debadeepta Dey.
International Conference on Learning Representations (ICLR) Blog, 2022

Towards Deeper Generative Architectures for GANs using Dense connections
Samarth Tripathi, Renbo Tu.