Mark Braverman — accepted AI-conference papers

2023

Understanding Influence Functions and Datamodels via Harmonic Analysis

Nikunj Saunshi, Arushi Gupta, Mark Braverman, Sanjeev Arora

ICLR 2023poster

Influence functions estimate effect of individual data points on predictions of the model on test data and were adapted to deep learning in \cite{koh2017understanding}. They have been used for detecting data poisoning, detecting helpful and harmful examples, influence of groups of datapoints, etc. R…

Cited by 30 Source ↗PDF ↗Scholar ↗

2020

Calibration, Entropy Rates, and Memory in Language Models

Mark Braverman, Xinyi Chen, Sham Kakade, Karthik Narasimhan, Cyril Zhang, Yi Zhang

ICML 2020poster

Building accurate language models that capture meaningful long-term dependencies is a core challenge in natural language processing. Towards this end, we present a calibration-based approach to measure long-term discrepancies between a generative sequence model and the true distribution, and use the…

Cited by 46 Source ↗PDF ↗Scholar ↗