Optimal Variance Control of the Score-Function Gradient Estimator for Importance Weighted Bounds
Research output: Contribution to journal › Conference article › Research › peer-review
Final published version, 1.89 MB, PDF document
This paper introduces novel results for the score function gradient estimator of the importance weighted variational bound (IWAE). We prove that in the limit of large K (number of importance samples) one can choose the control variate such that the Signal-to-Noise ratio (SNR) of the estimator grows as pK. This is in contrast to the standard pathwise gradient estimator where the SNR decreases as 1/pK. Based on our theoretical findings we develop a novel control variate that extends on VIMCO. Empirically, for the training of both continuous and discrete generative models, the proposed method yields superior variance reduction, resulting in an SNR for IWAE that increases with K without relying on the reparameterization trick. The novel estimator is competitive with state-of-the-art reparameterization-free gradient estimators such as Reweighted Wake-Sleep (RWS) and the thermodynamic variational objective (TVO) when training generative models.
|Journal||Advances in Neural Information Processing Systems|
|Number of pages||12|
|Publication status||Published - 2020|
|Event||34th Conference on Neural Information Processing Systems, NeurIPS 2020 - Virtual, Online|
Duration: 6 Dec 2020 → 12 Dec 2020
|Conference||34th Conference on Neural Information Processing Systems, NeurIPS 2020|
|Period||06/12/2020 → 12/12/2020|
|Sponsor||Apple, et al., Microsoft, PDT Partners, Sony Group Corporation, Tenstorrent|
© 2020 Neural information processing systems foundation. All rights reserved.