Risk-controlling model selection via guided bayesian optimization
Adjustable hyperparameters of machine learning models typically impact various key trade-
offs such as accuracy, fairness, robustness, or inference cost. Our goal in this paper is to find …
offs such as accuracy, fairness, robustness, or inference cost. Our goal in this paper is to find …
Semi-Supervised Risk Control via Prediction-Powered Inference
The risk-controlling prediction sets (RCPS) framework is a general tool for transforming the
output of any machine learning model to design a predictive rule with rigorous error rate …
output of any machine learning model to design a predictive rule with rigorous error rate …
Fast yet Safe: Early-Exiting with Risk Control
Scaling machine learning models significantly improves their performance. However, such
gains come at the cost of inference being slow and resource-intensive. Early-exit neural …
gains come at the cost of inference being slow and resource-intensive. Early-exit neural …
Streamlining Conformal Information Retrieval via Score Refinement
Information retrieval (IR) methods, like retrieval augmented generation, are fundamental to
modern applications but often lack statistical guarantees. Conformal prediction addresses …
modern applications but often lack statistical guarantees. Conformal prediction addresses …
Confident magnitude-based neural network pruning
Pruning neural networks has proven to be a successful approach to increase the efficiency
and reduce the memory storage of deep learning models without compromising …
and reduce the memory storage of deep learning models without compromising …