1 code implementation • 3 Nov 2022 • Divyat Mahajan, Ioannis Mitliagkas, Brady Neal, Vasilis Syrgkanis
We study the problem of model selection in causal inference, specifically for the case of conditional average treatment effect (CATE) estimation under binary treatments.
no code implementations • 30 Nov 2020 • Brady Neal, Chin-wei Huang, Sunand Raghupathi
However, the best causal estimators on synthetic data are unlikely to be the best causal estimators on real data.
1 code implementation • NeurIPS 2020 • Gintare Karolina Dziugaite, Alexandre Drouin, Brady Neal, Nitarshan Rajkumar, Ethan Caballero, Linbo Wang, Ioannis Mitliagkas, Daniel M. Roy
A large volume of work aims to close this gap, primarily by developing bounds on generalization error, optimization error, and excess risk.
no code implementations • 17 Dec 2019 • Brady Neal
Through extensive experiments and analysis, we show a lack of a bias-variance tradeoff in neural networks when increasing network width.
no code implementations • ICML Workshop Deep_Phenomen 2019 • Brady Neal, Ioannis Mitliagkas
There is significant recent evidence in supervised learning that, in the over-parametrized setting, wider networks achieve better test error.
no code implementations • 19 Oct 2018 • Brady Neal, Sarthak Mittal, Aristide Baratin, Vinayak Tantia, Matthew Scicluna, Simon Lacoste-Julien, Ioannis Mitliagkas
The bias-variance tradeoff tells us that as model complexity increases, bias falls and variances increases, leading to a U-shaped test error curve.
no code implementations • ICLR 2018 • Brady Neal, Alex Lamb, Sherjil Ozair, Devon Hjelm, Aaron Courville, Yoshua Bengio, Ioannis Mitliagkas
One of the most successful techniques in generative models has been decomposing a complicated generation task into a series of simpler generation tasks.
no code implementations • 16 Dec 2017 • Ryan Turner, Brady Neal
We present a new data-driven benchmark system to evaluate the performance of new MCMC samplers.