no code implementations • 5 Feb 2023 • Yadi Wei, Roni Khardon
In contrast, Bayesian neural networks provide good uncertainty quantification but optimizing them is time consuming due to the large parameter space.
no code implementations • 15 Nov 2022 • Yadi Wei, Roni Khardon
Direct Loss Minimization (DLM) has been proposed as a pseudo-Bayesian method motivated as regularized loss minimization.
1 code implementation • 7 Apr 2020 • Yadi Wei, Rishit Sheth, Roni Khardon
The application of DLM in non-conjugate cases is more complex because the logarithm of expectation in the log-loss DLM objective is often intractable and simple sampling leads to biased estimates of gradients.