166 citations · 595 across the 71 of their papers we have counts for
10 papers · 1 filter
MultiRisk: Multiple Risk Control via Iterative Score Thresholding
Sunay Joshi, Yan Sun, Hamed Hassani +1
As generative AI systems are increasingly deployed in real-world applications, regulating multiple dimensions of model behavior has become essential. We focus on test-time filterin…
Fair Classification by Direct Intervention on Operating Characteristics
Kevin Jiang, Edgar Dobriban
We develop new classifiers under group fairness in the attribute-aware setting for binary classification with multiple group fairness constraints (e.g., demographic parity (DP), eq…
Statistical Methods in Generative AI
Edgar Dobriban
Generative Artificial Intelligence is emerging as an important technology, promising to be transformative in many areas. At the same time, generative AI techniques are based on sam…
Singleton-Optimized Conformal Prediction
Tao Wang, Yan Sun, Edgar Dobriban
Conformal prediction can be used to construct prediction sets that cover the true outcome with a desired probability, but can sometimes lead to large prediction sets that are costl…
General Synthetic-Powered Inference
Meshi Bashari, Yonghoon Lee, Roy Maor Lotan +2
The rapid proliferation of high-quality synthetic data -- generated by advanced AI models or collected as auxiliary data from related tasks -- presents both opportunities and chall…
Conformal Information Pursuit for Interactively Guiding Large Language Models
Kwan Ho Ryan Chan, Yuyan Ge, Edgar Dobriban +2
A significant use case of instruction-finetuned Large Language Models (LLMs) is to solve question-answering tasks interactively. In this setting, an LLM agent is tasked with making…
Synthetic-Powered Predictive Inference
Meshi Bashari, Roy Maor Lotan, Yonghoon Lee +2
Conformal prediction is a framework for predictive inference with a distribution-free, finite-sample guarantee. However, it tends to provide uninformative prediction sets when cali…
Foundations of Top- Decoding For Language Models
Georgy Noarov, Soham Mallick, Tao Wang +5
Top- decoding is a widely used method for sampling from LLMs: at each token, only the largest next-token-probabilities are kept, and the next token is sampled after re-norma…
Finding Distributions that Differ, with False Discovery Rate Control
Yonghoon Lee, Edgar Dobriban, Eric Tchetgen Tchetgen
We consider the problem of comparing a reference distribution with several other distributions. Given a sample from both the reference and the comparison groups, we aim to identify…
Conformal Inference under High-Dimensional Covariate Shifts via Likelihood-Ratio Regularization
Sunay Joshi, Shayan Kiyani, George Pappas +2
We consider the problem of conformal prediction under covariate shift. Given labeled data from a source domain and unlabeled data from a covariate shifted target domain, we seek to…