Karl Krauth

PhD Student in Machine Learning

UC Berkeley

Biography

I am a fifth year PhD student in computer science at the University of California, Berkeley, advised by Jonathan Ragan-Kelley and Michael I. Jordan. I am a member of the RISELab and Berkeley AI Research.

Prior to coming to Berkeley I completed my undergraduate degree in computer science at the University of New South Wales where I was supervised by Gernot Heiser for my honour’s thesis. I also had the good fortune of working with Edwin Bonilla as a research assistant.

Recent Publications

*: Equal contribution

Jiri Hron, Karl Krauth, Michael I. Jordan, Niki Kilbertus. On Component Interaction in Two-Stage Recommender Systems. In NeurIPS, 2021.

PDF

Wenshuo Guo*, Karl Krauth*, Michael I. Jordan, Nikhil Garg. The Stereotyping Problem in Collaboratively Filtered Recommender Systems. In ACM EAAMO, 2021.

PDF

Karl Krauth, Sarah Dean*, Alex Zhao*, Wenshuo Guo*, Mihaela Curmei*, Benjamin Recht, Michael I. Jordan. Do Offline Metrics Predict Online Performance in Recommender Systems?. Under Review, 2020.

Jiri Hron*, Karl Krauth*, Michael I. Jordan, Niki Kilbertus. Exploration in Two-Stage Recommender Systems. In REVEAL, 2020.

John Miller, Karl Krauth, Benjamin Recht, Ludwig Schmidt. The Effect of Natural Distribution Shift on Question Answering Models. In ICML, 2020.

PDF

Vaishaal Shankar, Karl Krauth, Qifan Pu, Eric Jonas, Shivaram Venkataraman, Ion Stoica, Benjamin Recht, Jonathan Ragan-Kelley. numpywren: Serverless Linear Algebra. In SoCC, 2020.

PDF

Karl Krauth*, Stephen Tu*, Benjamin Recht. Finite-time Analysis of Approximate Policy Iteration for the Linear Quadratic Regulator. In NeurIPS, 2019.

PDF

Edwin Bonilla*, Karl Krauth*, Amir Dezfouli. Generic Inference in Latent Gaussian Process Models. In JMLR, 2019.

PDF

Eric Jonas, Johann Schleier-Smith, Vikram Sreekanti, Chia-Che Tsai, Anurag Khandelwal, Qifan Pu, Vaishaal Shankar, Joao Menezes Carreira, Karl Krauth, Neeraja Yadwadkar, Joseph Gonzalez, Raluca Ada Popa, Ion Stoica, David A. Patterson. Cloud Programming Simplified: A Berkeley View on Serverless Computing. 2019.

PDF

Karl Krauth, Edwin Bonilla, Kurt Cutajar, Maurizio Filippone. AutoGP: Exploring the Capabilities and Limitations of Gaussian Process Models. In UAI, 2017.

PDF Code

Karl Krauth

PhD Student in Machine Learning

UC Berkeley

Biography

Recent Publications

Contact