activity
20192022
most citedNeural Kernels Without Tangents

33 citations · 49 across the 9 of their papers we have counts for

collaborators

14 papers

cs.LG2023

Reward Learning as Doubly Nonparametric Bandits: Optimal Design and Scaling Laws

Kush Bhatia, Wenshuo Guo, Jacob Steinhardt

Specifying reward functions for complex tasks like object manipulation or driving is challenging to do by hand. Reward learning seeks to address this by learning a reward model usi…

cs.GT2023

Leveraging Reviews: Learning to Price with Buyer and Seller Uncertainty

Wenshuo Guo, Nika Haghtalab, Kirthevasan Kandasamy +1

In online marketplaces, customers have access to hundreds of reviews for a single product. Buyers often use reviews from other customers that share their type -- such as height for…

cs.LG20222 cited

Partial Identification with Noisy Covariates: A Robust Optimization Approach

Wenshuo Guo, Mingzhang Yin, Yixin Wang +1

Causal inference from observational datasets often relies on measuring and adjusting for covariates. In practice, measurements of the covariates can often be noisy and/or biased, o…

cs.IT2022

Polynomial-Time Key Recovery Attack on the Lau-Tan Cryptosystem Based on Gabidulin Codes

Wenshuo Guo, Fang-Wei Fu

This paper presents a key recovery attack on the cryptosystem proposed by Lau and Tan in a talk at ACISP 2018. The Lau-Tan cryptosystem uses Gabidulin codes as the underlying decod…

cs.GT20211 cited

Robust Learning of Optimal Auctions

Wenshuo Guo, Michael I. Jordan, Manolis Zampetakis

We study the problem of learning revenue-optimal multi-bidder auctions from samples when the samples of bidders' valuations can be adversarially corrupted or drawn from distributio…

cs.LG2021

Test-time Collective Prediction

Celestine Mendler-Dünner, Wenshuo Guo, Stephen Bates +1

An increasingly common setting in machine learning involves multiple parties, each with their own data, who want to jointly make predictions on future test points. Agents wish to b…