Yash Savani

About Me

Hi! I am a second-year Ph.D. student in the Computer Science Department at Carnegie Mellon University supervised by Prof. Zico Kolter. I am broadly interested in all aspects of machine learning, both theoretical and applied. I have four years of industry experience operationalizing contemporary machine learning research for real-world applications. This experience has highlighted several potentially valuable research opportunities and holes in the literature, some of which I am currently exploring. My current research interests are robust deep learning, distributional shift, and adversarial learning.

Education

• Ph.D. in Computer Science. (GPA 0.00 / 0.00)

  Aug 2021 - Current

  Carnegie Mellon University Pittsburgh, PA

• M.S. in Statistics. (GPA 3.77 / 4.00)

  Mar 2015 - Jun 2017

  Stanford University Palo Alto, CA

• B.S. in Computer Science. (GPA 3.54 / 4.00)

  Sep 2013 - Jun 2017

  Stanford University Palo Alto, CA

Experience

• Research Scientist at Abacus.AI

  San Francisco, CA

  May 2020 - May 2021

  I performed research in the AutoML / NAS and Fairness in ML domains. We wrote five papers based on this work.

• Machine Learning Engineer at Abacus.AI

  San Francisco, CA

  Apr 2019 - May 2020

  I designed and implemented scalable deep learning architectures including LSTM forecasting models, AutoML / NAS regression and classification models, GAN data augmentation models, and VAE anomaly detection models among others.

• Machine Learning Engineer at Primer.AI

  San Francisco, CA

  Aug 2017 - Dec 2018

  I worked on improving contemporary statistical learning and applied graph theory models for natural language applications. The machine intelligence algorithms I developed help decipher global news data.

• Research Intern at Andrew Ng's Artificial Intelligence Lab

  Stanford University, CA

  Jul 2015 - Sep 2015

  I worked on the system infrastructure and CUDA code for a hybrid CNN and LSTM architecture designed to instantly detect and semantically segment images and videos with multiple stimuli.

• Cofounder (CTO) at Ebotic, Inc.

  Palo Alto, CA

  Jul 2014 - Dec 2015

  I worked with an international team to develop an intelligent drone platform that applied advanced flight technologies, SLAM, and deep learning for improved flight stability and awareness.

• Research Intern at Sebastian Thrun's Artificial Intelligence Lab

  Stanford University, CA

  Jun 2014 - Aug 2014

  I improved the performance of machine learning algorithms for smart home applications by adding thermal image descriptors into a robotics pipeline.

Skills

Commonly used skills are highlighted.

• Computer Languages

  Python, Julia, C / C++, CUDA, Javascript, R, Java, MATLAB, Racket, Haskell, LaTeX, SQL, NoSQL, and HTML5 / CSS3.

• Frameworks / Tools

  PyTorch, TensorFlow, NumPy, Matplotlib, Jupyter, SpaCy, Nltk, AllenNLP, Linux, AWS, GCP, Docker, Git, Visual Studio Code, Vim, React, Redux, Webpack, Flask, Blender, Photoshop, and Figma.

• Other Interests

  Analysis, algebra, topology, incentive theory, economics, cognitive science, neuroscience, videography, scuba diving, rock climbing, and fitness.

Conference Publications

• 2022

  • Deep Equilibrium Optical Flow Estimation.

    S. Bai, Z. Geng, Y. Savani, J. Z. Kolter.

    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022.

• 2021

  • NAS-Bench-x11 and the Power of Learning Curves.

    S. Yan, C. White, Y. Savani, F. Hutter.

    Advances in Neural Information Processing Systems (NeurIPS) 2021.

  • Exploring the Loss Landscape in Neural Architecture Search.

    C. White, S. Nolen, Y.Savani.

    Conference on Uncertainty in Artificial Intelligence (UAI). PMLR, 2021.

  • BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search.

    C. White, W. Neiswanger, Y. Savani.

    Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) 2021.

• 2020

  • Intra-Processing Methods for Debiasing Neural Networks.

    Y. Savani, C. White, N. S. Govindarajulu.

    Advances in Neural Information Processing Systems (NeurIPS) 2020.

  • A Study on Encodings for Neural Architecture Search.

    C. White, W. Neiswanger, S. Nolen, Y. Savani.

    Advances in Neural Information Processing Systems (NeurIPS) 2020.

Workshop Publications

• 2020

  • A Study on Encodings for Neural Architecture Search.

    Poster

    C. White, W. Neiswanger, S. Nolen, Y. Savani.

    ICML Workshop on AutoML, 2020.

  • Local Search is State of the Art for Neural Architecture Search Benchmarks.

    Poster

    C. White, S. Nolen, Y. Savani.

    ICML Workshop on AutoML, 2020.

• 2019

  • Neural Architecture Search via Bayesian Optimization with a Neural Network Prior.

    C. White, W. Neiswanger, Y. Savani.

    NeurIPS Workshop on Meta Learning, 2019.

  • Deep Uncertainty Estimation for Model-based Neural Architecture Search.

    C. White, W. Neiswanger, Y. Savani.

    NeurIPS Workshop on Bayesian Deep Learning, 2019.