43 citations · 288 across the 47 of their papers we have counts for
8 papers · 1 filter
Meta-Reflective Evolution Effectively Improves Production AI Systems
Seung Won Wilson Yoo, Chang Zeng, Aditi Somayajula +7
Large Language Model (LLM)-guided evolutionary optimization has successfully improved prompts, programs, and even entire AI systems. Most optimization methods select a candidate fr…
Rethinking Streaming Machine Learning Evaluation
Shreya Shankar, Bernease Herman, Aditya G. Parameswaran
While most work on evaluating machine learning (ML) models focuses on computing accuracy on batches of data, tracking accuracy alone in a streaming setting (i.e., unbounded, timest…
Demystifying a Dark Art: Understanding Real-World Machine Learning Model Development
Angela Lee, Doris Xin, Doris Lee +1
It is well-known that the process of developing machine learning (ML) workflows is a dark-art; even experts struggle to find an optimal workflow leading to a high accuracy model. U…
Helix: Accelerating Human-in-the-loop Machine Learning
Doris Xin, Litian Ma, Jialin Liu +3
Data application developers and data scientists spend an inordinate amount of time iterating on machine learning (ML) workflows -- by modifying the data pre-processing, model train…
How Developers Iterate on Machine Learning Workflows -- A Survey of the Applied Machine Learning Literature
Doris Xin, Litian Ma, Shuchen Song +1
Machine learning workflow development is anecdotally regarded to be an iterative process of trial-and-error with humans-in-the-loop. However, we are not aware of quantitative evide…
The Importance of Norm Regularization in Linear Graph Embedding: Theoretical Analysis and Empirical Demonstration
Yihan Gao, Chao Zhang, Jian Peng +1
Learning distributed representations for nodes in graphs is a crucial primitive in network analysis with a wide spectrum of applications. Linear graph embedding methods learn such…
On the Interpretability of Conditional Probability Estimates in the Agnostic Setting
Yihan Gao, Aditya Parameswaran, Jian Peng
We study the interpretability of conditional probability estimates for binary classification under the agnostic setting or scenario. Under the agnostic setting, conditional probabi…
Indexing Cost Sensitive Prediction
Leilani Battle, Edward Benson, Aditya Parameswaran +1
Predictive models are often used for real-time decision making. However, typical machine learning techniques ignore feature evaluation cost, and focus solely on the accuracy of the…