AI Paper Atlas

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

NAS-X: Neural Adaptive Smoothing via Twisting

Dieterich Lawson, Michael Y. Li, Scott Linderman

NeurIPS 2023 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Sequential Monte Carlo for inference · 0 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
Use NAS-X instead of SIXOHH inference, proposals trained with 4 particles · Squid giant axon HHlog-likelihood lower bound: NAS-X outperforms SIXO by roughly 34 nats at 4 particlesImproved
Use NAS-X instead of NASMCHH inference · Squid giant axon HHparticle efficiency: 4 particles; 256 particles; 64-times increaseImproved
Use NAS-X instead of SIXOHH inference · Squid giant axon HHparticle efficiency: 2x particle efficiency improvementImproved
Increase the number of training particlesNAS-X · Squid giant axon HHinference performanceNo clear effect
Increase the number of training particlesVI-based methods · Squid giant axon HHinference performanceHurt
Use a bootstrap proposal instead of FIVO's parametric proposalFIVO · Squid giant axon HHlog-likelihood lower boundImproved
Use NAS-X instead of SIXOMouse pyramidal neuron model learning · Mouse pyramidal neuronspike count errorImproved
Use NAS-X instead of SIXOMouse pyramidal neuron model learning · Mouse pyramidal neurontest log-likelihood lower boundHurt
Use NAS-X instead of SIXOMouse pyramidal neuron model learning · Mouse pyramidal neurontraining-run failure rateImproved
Use NAS-X instead of SIXOHH model training with the reported particle counts · Squid giant axon HHtraining bound: NAS-X: -664.3528; SIXO: -668.6865; NAS-X: -662.8712; SIXO: -653.6352; NAS-X: -662.0753; SIXO: -644.8764; NAS-X: -661.538Mixed
Use NAS-X instead of SIXOHH bootstrap evaluation · Squid giant axon HHBPF bound (256 particles): -660.7003 -> -636.2579Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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