565 citations · 756 across the 13 of their papers we have counts for
14 papers
Breaking Feedback Loops in Recommender Systems with Causal Inference
Karl Krauth, Yixin Wang, Michael I. Jordan
Recommender systems play a key role in shaping modern web ecosystems. These systems alternate between (1) making recommendations (2) collecting user responses to these recommendati…
Recommendation Systems with Distribution-Free Reliability Guarantees
Anastasios N. Angelopoulos, Karl Krauth, Stephen Bates +2
When building recommendation systems, we seek to output a helpful set of items to the user. Under the hood, a ranking model predicts which of two candidate items is better, and we…
Modeling Content Creator Incentives on Algorithm-Curated Platforms
Jiri Hron, Karl Krauth, Michael I. Jordan +2
Content creators compete for user attention. Their reach crucially depends on algorithmic choices made by developers on online platforms. To maximize exposure, many creators adapt…
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao +448
Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabil…
On component interactions in two-stage recommender systems
Jiri Hron, Karl Krauth, Michael I. Jordan +1
Thanks to their scalability, two-stage recommenders are used by many of today's largest online platforms, including YouTube, LinkedIn, and Pinterest. These systems produce recommen…
The Stereotyping Problem in Collaboratively Filtered Recommender Systems
Wenshuo Guo, Karl Krauth, Michael I. Jordan +1
Recommender systems play a crucial role in mediating our access to online information. We show that such algorithms induce a particular kind of stereotyping: if preferences for a s…
Do Offline Metrics Predict Online Performance in Recommender Systems?
Karl Krauth, Sarah Dean, Alex Zhao +4
Recommender systems operate in an inherently dynamical setting. Past recommendations influence future behavior, including which data points are observed and how user preferences ch…
Exploration in two-stage recommender systems
Jiri Hron, Karl Krauth, Michael I. Jordan +1
Two-stage recommender systems are widely adopted in industry due to their scalability and maintainability. These systems produce recommendations in two steps: (i) multiple nominato…
The Effect of Natural Distribution Shift on Question Answering Models
John Miller, Karl Krauth, Benjamin Recht +1
We build four new test sets for the Stanford Question Answering Dataset (SQuAD) and evaluate the ability of question-answering systems to generalize to new data. Our first test set…
Finite-time Analysis of Approximate Policy Iteration for the Linear Quadratic Regulator
Karl Krauth, Stephen Tu, Benjamin Recht
We study the sample complexity of approximate policy iteration (PI) for the Linear Quadratic Regulator (LQR), building on a recent line of work using LQR as a testbed to understand…
Cloud Programming Simplified: A Berkeley View on Serverless Computing
Eric Jonas, Johann Schleier-Smith, Vikram Sreekanti +11
Serverless cloud computing handles virtually all the system administration operations needed to make it easier for programmers to use the cloud. It provides an interface that great…
numpywren: serverless linear algebra
Vaishaal Shankar, Karl Krauth, Qifan Pu +5
Linear algebra operations are widely used in scientific computing and machine learning applications. However, it is challenging for scientists and data analysts to run linear algeb…
AutoGP: Exploring the Capabilities and Limitations of Gaussian Process Models
Karl Krauth, Edwin V. Bonilla, Kurt Cutajar +1
We investigate the capabilities and limitations of Gaussian process models by jointly exploring three complementary directions: (i) scalable and statistically efficient inference;…
Generic Inference in Latent Gaussian Process Models
Edwin V. Bonilla, Karl Krauth, Amir Dezfouli
We develop an automated variational method for inference in models with Gaussian process (GP) priors and general likelihoods. The method supports multiple outputs and multiple late…