Search Results for author:
Found 10 papers, 5 papers with code
Social Environment Design
Artificial Intelligence (AI) holds promise as a technology that can be used to improve government and economic policy-making.
Computing Voting Rules with Elicited Incomplete Votes
Motivated by the difficulty of specifying complete ordinal preferences over a large set of $m$ candidates, we study voting rules that are computable by querying voters about $t < m$ candidates.
Multi-Sender Persuasion -- A Computational Perspective
The core solution concept here is the Nash equilibrium of senders' signaling policies.
Equilibrium of Data Markets with Externality
Starting with a simple setting where buyers know their valuations a priori, we characterize both the existence and welfare properties of the pure Nash equilibrium in the presence of such externality.
Exploring Text Specific and Blackbox Fairness Algorithms in Multimodal Clinical NLP
Clinical machine learning is increasingly multimodal, collected in both structured tabular formats and unstructured forms such as freetext.
Fair Algorithms for Multi-Agent Multi-Armed Bandits
Unlike the classical multi-armed bandit problem, the goal is not to learn the "best arm"; indeed, each agent may perceive a different arm to be the best for her personally.
JacNet: Learning Functions with Structured Jacobians
Neural networks are trained to learn an approximate mapping from an input domain to a target domain.
Generative Adversarial Networks for text using word2vec intermediaries
Generative adversarial networks (GANs) have shown considerable success, especially in the realistic generation of images.
ChainGAN: A sequential approach to GANs
Current approaches attempt to learn the transformation from a noise sample to a generated data sample in one shot.
DeepConsensus: using the consensus of features from multiple layers to attain robust image classification
We consider a classifier whose test set is exposed to various perturbations that are not present in the training set.
