69 citations · 127 across the 14 of their papers we have counts for
14 papers
Causal Survival Forests with Negative Controls
Zijun Gao, Kyoungeui Hong, Leyi Ma +3
We study heterogeneous treatment-effect (HTE) estimation in observational survival studies commonly associated with both censored outcomes and unmeasured confounding. We integrate…
Tracing LLM Behavior to the Training Data with Empirical Next-Token Distributions
Zachary Izzo
In this paper, we study the connection between an LLM's output distribution and the data used to train it. Specifically, we study the degree to which an LLM's next-token distributi…
Subgroup Discovery with the Cox Model
Zachary Izzo, Iain Melvin
We study the problem of subgroup discovery for survival analysis, where the goal is to find an interpretable subset of the data on which a Cox model is highly accurate. Our work is…
To Err Is Human: Systematic Quantification of Errors in Published AI Papers via LLM Analysis
Federico Bianchi, Yongchan Kwon, Zachary Izzo +2
How many mistakes do published AI papers contain? Peer-reviewed publications form the foundation upon which new research and knowledge are built. Errors that persist in the literat…
Quantitative Bounds for Length Generalization in Transformers
Zachary Izzo, Eshaan Nichani, Jason D. Lee
We study the problem of length generalization (LG) in transformers: the ability of a model trained on shorter sequences to maintain performance when evaluated on much longer, previ…
Group Relative Augmentation for Data Efficient Action Detection
Deep Anil Patel, Iain Melvin, Zachary Izzo +1
Adapting large Video-Language Models (VLMs) for action detection using only a few examples poses challenges like overfitting and the granularity mismatch between scene-level pre-tr…
Solving Inverse Problems via Diffusion-Based Priors: An Approximation-Free Ensemble Sampling Approach
Haoxuan Chen, Yinuo Ren, Martin Renqiang Min +2
Diffusion models (DMs) have proven to be effective in modeling high-dimensional distributions, leading to their widespread adoption for representing complex priors in Bayesian inve…
Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews
Weixin Liang, Zachary Izzo, Yaohui Zhang +9
We present an approach for estimating the fraction of text in a large corpus which is likely to be substantially modified or produced by a large language model (LLM). Our maximum l…
Data-Driven Subgroup Identification for Linear Regression
Zachary Izzo, Ruishan Liu, James Zou
Medical studies frequently require to extract the relationship between each covariate and the outcome with statistical confidence measures. To do this, simple parametric models are…
Provable Membership Inference Privacy
Zachary Izzo, Jinsung Yoon, Sercan O. Arik +1
In applications involving sensitive data, such as finance and healthcare, the necessity for preserving data privacy can be a significant barrier to machine learning model developme…
How to Learn when Data Gradually Reacts to Your Model
Zachary Izzo, James Zou, Lexing Ying
A recent line of work has focused on training machine learning (ML) models in the performative setting, i.e. when the data distribution reacts to the deployed model. The goal in th…
Dimensionality Reduction for Wasserstein Barycenter
Zachary Izzo, Sandeep Silwal, Samson Zhou
The Wasserstein barycenter is a geometric construct which captures the notion of centrality among probability distributions, and which has found many applications in machine learni…
How to Learn when Data Reacts to Your Model: Performative Gradient Descent
Zachary Izzo, Lexing Ying, James Zou
Performative distribution shift captures the setting where the choice of which ML model is deployed changes the data distribution. For example, a bank which uses the number of open…
Approximate Data Deletion from Machine Learning Models
Zachary Izzo, Mary Anne Smart, Kamalika Chaudhuri +1
Deleting data from a trained machine learning (ML) model is a critical task in many applications. For example, we may want to remove the influence of training points that might be…