AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Energy-Based Sliced Wasserstein Distance

Khai Nguyen, Nhat Ho

NeurIPS 2023 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Posterior sampling with diffusion guidance · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace uniform slicing (SW) with IS-EBSW-e energy-based slicingsliced Wasserstein distance · point-cloud gradient flow, step 500Wasserstein-2 (x10^4): 9.41 -> 3.3Improved
replace Max-SW with IS-EBSW-esliced Wasserstein distance · point-cloud gradient flow, step 500Wasserstein-2 (x10^4): 6.83 -> 3.3Improved
replace v-DSW with IS-EBSW-esliced Wasserstein distance · point-cloud gradient flow, step 500Wasserstein-2 (x10^4): 5.68 -> 3.3Improved
replace Max-SW with IS-EBSW-esliced Wasserstein distance · point-cloud gradient flowcomputation time (s): 28.38 -> 17.63Improved
replace v-DSW with IS-EBSW-esliced Wasserstein distance · point-cloud gradient flowcomputation time (s): 21.2 -> 17.63Improved
replace SW with IS-EBSW-esliced Wasserstein distance · point-cloud gradient flowcomputation time (s): 17.06 -> 17.63No clear effect
use exponential energy function instead of identity energy function (ablation)EBSW · point-cloud gradient flowWasserstein-2Improved
use SIR, IMH or RMH sampling instead of importance sampling (ablation)EBSW-e · point-cloud gradient flowWasserstein-2 and timeNo clear effect
replace SW with IS-EBSW-epoint-cloud autoencoder · ModelNet40, epoch 20SW2: 2.97 -> 2.68Improved
replace SW with IS-EBSW-epoint-cloud autoencoder · ModelNet40, epoch 20W2: 12.67 -> 11.90Improved
replace Max-SW with IS-EBSW-epoint-cloud autoencoder · ModelNet40, epoch 200W2: 9.84 -> 9.69Improved
replace v-DSW with IS-EBSW-epoint-cloud autoencoder · ModelNet40, epoch 200SW2: 2.07 -> 2.04Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy