6 papers
The Impact of Likelihood Tempering on the Limiting Predictive Moments of Variational Bayesian Linear Neural Networks
Ian Zhang, Thibault Randrianarisoa
In wide Bayesian neural networks, Gaussian mean-field variational inference is prone to "prior dominance": the Kullback-Leibler (KL) regularization term of the ELBO outweighs the e…
Hallucination Rates in Language Generation
Debmalya Panigrahi, Fan Wei, Ian Zhang
Language generation in the limit is an elegant model introduced by Kleinberg and Mullainathan [KM24] to formally study language generation by an algorithm that learns solely based…
Characterizing the Effect of Noise in Language Generation in the Limit
Aaron Li, Ian Zhang
Kleinberg and Mullainathan recently proposed a formal framework for studying the phenomenon of language generation, called language generation in the limit. In this model, an adver…
Deliberation via Matching
Kamesh Munagala, Qilin Ye, Ian Zhang
We study deliberative social choice, where voters engage in small-group discussions to output collective preferences that are then aggregated by a social choice rule. We introduce…
Language Generation in the Limit: Noise, Loss, and Feedback
Yannan Bai, Debmalya Panigrahi, Ian Zhang
Kleinberg and Mullainathan (2024) recently proposed a formal framework called language generation in the limit and showed that given a sequence of example strings from an unknown t…
Fair Division via the Cake-Cutting Share
Yannan Bai, Kamesh Munagala, Yiheng Shen +1
In this paper, we consider the classic fair division problem of allocating divisible items to agents with linear valuations over the items. We define novel notions of fair…