Jacob Gardner, Osbert Bastani, Yimeng Zeng, Michael Yao, Hamsa Bastani, James Gee
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Offline model-based optimization seeks to optimize against a learned surrogate model without querying the true oracle objective function during optimization. Such tasks are commonly encountered in protein design, robotics, and clinical medicine where evaluating the oracle function is prohibitively expensive. However, inaccurate surrogate model predictions are frequently encountered along offline optimization trajectories. To address this limitation, we propose generative adversarial model-based optimization using adaptive source critic regularization (aSCR)-a task-and optimizer-agnostic framework for constraining the optimization trajectory to regions of the design space where the surrogate function is reliable. We propose a computationally tractable algorithm to dynamically adjust the strength of this constraint, and show how leveraging aSCR with standard Bayesian optimization outperforms existing methods on a suite of offline generative design tasks. Our code is available at https://github.com/michael-s-yao/gabo.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2402.06532")
get_code_for_paper("2402.06532")
have("2402.06532")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2402.06532.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2402.06532)
Connect an agent — have() is free.