Reparameterization Tricks: Variance Reduction by Smarter Gradients
It works by moving randomness outside the computation graph and turns an awkward gradient of an expectation into an ordinary chain-rule derivative.A VAE is a generative model. An encoder maps input data xto a distribution over a latent variable z, while a decoder maps a sampled z back to a reconstruction of x. What makes it trainable is its objective, the ELBO (Evidence Lower Bound) i.e., a tractable stand-in for the true (intractable) data likelihood, made up of a reconstruction term and a term that regularizes the latent distribution toward a simple prior.
- ▪It works by moving randomness outside the computation graph and turns an awkward gradient of an expectation into an ordinary chain-rule derivative.A VAE is a generative model.
- ▪An encoder maps input data xto a distribution over a latent variable z, while a decoder maps a sampled z back to a reconstruction of x.
- ▪What makes it trainable is its objective, the ELBO (Evidence Lower Bound) i.e., a tractable stand-in for the true (intractable) data likelihood, made up of a reconstruction term and a term that regularizes the latent distribution toward a s
Towards Data Science files mainly under ai. We currently carry 148 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | Towards Data Science |
| Canonical URL | https://towardsdatascience.com/reparameterization-tricks-variance-reduction-by-smarter-gradients/ |
| Publication time | Tue, 15 Sep 2026 15:30:02 GMT |
| Retrieval time | 2026-09-15T15:31:52.719Z |
| Last seen | 2026-09-15T15:31:52.719Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | H8xTTWlvW368 · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Machine LearningReparameterization Tricks: Variance Reduction by Smarter GradientsHow moving randomness outside the computation graph turns noisy gradient estimators into low-variance, differentiable onesAnanya BhattacharyyaSeptember 15, 20269 min readGenerated by AI toolThe reparameterization trick is what makes Variational Autoencoders (VAEs) trainable with standard stochastic gradient descent. It works by moving randomness outside the computation graph and turns an awkward gradient of an expectation into an ordinary chain-rule derivative.A VAE is a generative model. An encoder maps input data xto a distribution over a latent variable z, while a decoder maps a sampled z back to a reconstruction of x.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Towards Data Science.
Discussion
0 commentsMore from Towards Data Science
