11 citations · 50 across the 10 of their papers we have counts for
10 papers
Neural Auctions Compromise Bidder Information
Alex Stein, Avi Schwarzschild, Michael Curry +2
Single-shot auctions are commonly used as a means to sell goods, for example when selling ad space or allocating radio frequencies, however devising mechanisms for auctions with mu…
Certified Neural Network Watermarks with Randomized Smoothing
Arpit Bansal, Ping-yeh Chiang, Michael Curry +5
Watermarking is a commonly used strategy to protect creators' rights to digital images, videos and audio. Recently, watermarking methods have been extended to deep learning models…
Analyzing Micro-Founded General Equilibrium Models with Many Agents using Deep Reinforcement Learning
Michael Curry, Alexander Trott, Soham Phade +2
Real economies can be modeled as a sequential imperfect-information game with many heterogeneous agents, such as consumers, firms, and governments. Dynamic general equilibrium (DGE…
Differentiable Economics for Randomized Affine Maximizer Auctions
Michael Curry, Tuomas Sandholm, John Dickerson
A recent approach to automated mechanism design, differentiable economics, represents auctions by rich function approximators and optimizes their performance by gradient descent. T…
Learning Revenue-Maximizing Auctions With Differentiable Matching
Michael J. Curry, Uro Lyi, Tom Goldstein +1
We propose a new architecture to approximately learn incentive compatible, revenue-maximizing auctions from sampled valuations. Our architecture uses the Sinkhorn algorithm to perf…
PreferenceNet: Encoding Human Preferences in Auction Design with Deep Learning
Neehar Peri, Michael J. Curry, Samuel Dooley +1
The design of optimal auctions is a problem of interest in economics, game theory and computer science. Despite decades of effort, strategyproof, revenue-maximizing auction designs…