Search Results for author:
Found 4 papers, 3 papers with code
Geographical Erasure in Language Generation
Large language models (LLMs) encode vast amounts of world knowledge.
Learning Action Embeddings for Off-Policy Evaluation
Off-policy evaluation (OPE) methods allow us to compute the expected reward of a policy by using the logged data collected by a different policy.
Optimizing Hyperparameters with Conformal Quantile Regression
Many state-of-the-art hyperparameter optimization (HPO) algorithms rely on model-based optimizers that learn surrogate models of the target function to guide the search.
Meta-Calibration Regularized Neural Networks
Our experiments show that (a) learning sample-wise gamma at continuous space can effectively perform calibration; (b) SECE smoothly optimise gamma-net towards better robustness to binning schemes; (c) the combination of gamma-net and SECE achieve the best calibration performance across various calibration metrics and retain very competitive predictive performance as compared to multiple recently proposed methods on three datasets.
