Fetching the paper…
Reading the bibliography…
In model-based optimisation (MBO) we are interested in using machine learning to design candidates that maximise some measure of reward with respect to a black box function called the (ground truth) oracle, which is expensive to compute since it involves executing a real world process.
The Fréchet distance between multivariate normal distributions
Dowson, DC and Landau, BV666017 · 1982
Earlier work this paper cites.
Principles of risk minimization for learning theory
Vapnik, Vladimir · 1991
Earlier work this paper cites.
Stochastic simulation: algorithms and analysis , volume 57
Asmussen, Søren and Glynn, Peter W · 2007
Earlier work this paper cites.
Bayesian learning via stochastic gradient langevin dynamics
Welling, Max and Teh, Yee W · 2011
Earlier work this paper cites.
Adam: A method for stochastic optimization
Kingma, Diederik P and Ba, Jimmy · 2014
Earlier work this paper cites.
How (not) to train your generative model: Scheduled sampling, likelihood, adversary?
Huszár, Ferenc · 2015
Earlier work this paper cites.
Deep unsupervised learning using nonequilibrium thermodynamics
Sohl-Dickstein, Jascha, Weiss, Eric, Maheswaranathan, Niru, and Ganguli, Surya · 2015
Earlier work this paper cites.
A note on the evaluation of generative models
Theis, Lucas, Oord, Aäron van den, and Bethge, Matthias · 2015
Earlier work this paper cites.
Generating images with perceptual similarity metrics based on deep networks
Dosovitskiy, Alexey and Brox, Thomas · 2016
Earlier work this paper cites.
GANs trained by a two time-scale update rule converge to a nash equilibrium
Heusel, Martin, Ramsauer, Hubert, Unterthiner, Thomas, Nessler, Bernhard, Klambauer, Günter, and Hochreiter, Sepp · 2017
Earlier work this paper cites.
Large scale gan training for high fidelity natural image synthesis
Brock, Andrew, Donahue, Jeff, and Simonyan, Karen · 2018
Earlier work this paper cites.
Understanding disentangling in beta-vae
Burgess, Christopher P, Higgins, Irina, Pal, Arka, Matthey, Loic, Watters, Nick, Desjardins, Guillaume, and Lerchner, Alexander · 2018
Earlier work this paper cites.
A data-driven statistical model for predicting the critical temperature of a superconductor
Hamidieh, Kam · 2018
Earlier work this paper cites.
Assessing generative models via precision and recall
Sajjadi, Mehdi SM, Bachem, Olivier, Lucic, Mario, Bousquet, Olivier, and Gelly, Sylvain · 2018
Cited alongside, same era.
Conditioning by adaptive sampling for robust design
Brookes, David, Park, Hahnbeom, and Listgarten, Jennifer · 2019
Cited alongside, same era.
Improved precision and recall metric for assessing generative models
Kynkäänniemi, Tuomas, Karras, Tero, Laine, Samuli, Lehtinen, Jaakko, and Aila, Timo · 2019
Cited alongside, same era.
Generative modeling by estimating gradients of the data distribution
Song, Yang and Ermon, Stefano · 2019
Cited alongside, same era.
Autofocused oracles for model-based design
Fannjiang, Clara and Listgarten, Jennifer · 2020
Cited alongside, same era.
Denoising diffusion probabilistic models
Ho, Jonathan, Jain, Ajay, and Abbeel, Pieter · 2020
Cited alongside, same era.
Conservative objective models for effective offline model-based optimization
Trabucco, Brandon, Kumar, Aviral, Geng, Xinyang, and Levine, Sergey · 2021
Later among the works it cites.
Pre-trained gaussian processes for bayesian optimization
Wang, Zi, Dahl, George E, Swersky, Kevin, Lee, Chansoo, Mariet, Zelda, Nado, Zachary, Gilmer, Justin, Snoek, Jasper, and Ghahramani, Zoubin · 2021
Later among the works it cites.
What are diffusion models?
Weng, Lilian · 2021
Later among the works it cites.
Few-shot bayesian optimization with deep kernel surrogates
Wistuba, Martin and Grabocka, Josif · 2021
Later among the works it cites.
Roma: Robust model adaptation for offline model-based optimization
Yu, Sihyun, Ahn, Sungsoo, Song, Le, and Shin, Jinwoo · 2021
Later among the works it cites.
Pros and cons of GAN evaluation measures: New developments
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Model inversion networks for model-based optimization
Kumar, Aviral and Levine, Sergey · 2020
Cited alongside, same era.
Reliable fidelity and diversity metrics for generative models
Naeem, Muhammad Ferjad, Oh, Seong Joon, Uh, Youngjung, Choi, Yunjey, and Yoo, Jaejun · 2020
Cited alongside, same era.
Making sense of reinforcement learning and probabilistic inference
O’Donoghue, Brendan, Osband, Ian, and Ionescu, Catalin · 2020
Cited alongside, same era.
Improved techniques for training score-based generative models
Song, Yang and Ermon, Stefano · 2020
Cited alongside, same era.
Diffusion models beat gans on image synthesis
Dhariwal, Prafulla and Nichol, Alexander · 2021
Cited alongside, same era.
Offline model-based optimization via normalized maximum likelihood estimation
Fu, Justin and Levine, Sergey · 2021
Cited alongside, same era.
Borji, Ali · 2022
Closest in time.
Bidirectional learning for offline infinite-width model-based optimization
Chen, Can, Zhang, Yingxueff, Fu, Jie, Liu, Xue (Steve), and Coates, Mark · 2022
Closest in time.
Classifier-free diffusion guidance
Ho, Jonathan and Salimans, Tim · 2022
Closest in time.
Local latent space bayesian optimization over structured inputs
Maus, Natalie, Jones, Haydn, Moore, Juston, Kusner, Matt J, Bradshaw, John, and Gardner, Jacob · 2022
Closest in time.
Implicit offline reinforcement learning via supervised learning
Piche, Alexandre, Pardinas, Rafael, Vazquez, David, Mordatch, Igor, and Pal, Chris · 2022
Closest in time.
Data-driven offline decision-making via invariant representation learning
Qi, Han, Su, Yi, Kumar, Aviral, and Levine, Sergey · 2022
Closest in time.
Design-bench: Benchmarks for data-driven offline model-based optimization
Trabucco, Brandon, Geng, Xinyang, Kumar, Aviral, and Levine, Sergey · 2022
Closest in time.