LGMLJun 7, 2018

Direct Optimization through $\arg \max$ for Discrete Variational Auto-Encoder

arXiv:1806.02867v521 citations
Originality Incremental advance
AI Analysis

This addresses a bottleneck in training discrete latent variable models for researchers in machine learning, though it appears incremental as it builds on existing direct loss minimization techniques.

The paper tackles the non-differentiability issue in discrete variational auto-encoders by proposing direct optimization through arg max, avoiding softmax relaxations, and demonstrates effectiveness in models with unstructured and structured discrete latent variables.

Reparameterization of variational auto-encoders with continuous random variables is an effective method for reducing the variance of their gradient estimates. In the discrete case, one can perform reparametrization using the Gumbel-Max trick, but the resulting objective relies on an $\arg \max$ operation and is non-differentiable. In contrast to previous works which resort to softmax-based relaxations, we propose to optimize it directly by applying the direct loss minimization approach. Our proposal extends naturally to structured discrete latent variable models when evaluating the $\arg \max$ operation is tractable. We demonstrate empirically the effectiveness of the direct loss minimization technique in variational autoencoders with both unstructured and structured discrete latent variables.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes