paper by Zachary Izzo, James Zou, Lexing Ying Presentation by
31/10/2022
Observation: individuals modify their behavior based on a low- dimensional proxy, such as a credit score or classification probability
How can we apply stateful PerfGD for a high-dimensional model without incurring a large error due to the high dimension?
$\mu_t = m(\theta_t,\mu_{t-1})= \bar{m}(s(\theta_t,\mu_{t-1}),\mu_{t-1})$ $s(\theta,\mu)\in \mathbb{R}^{d_s}$ and $d_s \ll dim(\theta)$
$\partial_1 s(\theta_t,\mu_{t-1})=\partial_1 \bar{m}(s_t,\mu_{t-1})\partial s(\theta_t,\mu_{t-1})$
^{}
_{ Reference:Strategic classification }
societal impacts: possibly maximize a certain measure of negative externality
future work: what are our assumptions?
deterministic MDP
batch setting
_{ Reference: Alternative microfoundations for strategic classification }