AI Paper Atlas

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

SIXO: Smoothing Inference with Twisted Objectives

Dieterich Lawson, Allan Raventos, Andrew Warrington, Scott Linderman

NeurIPS 2022 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Sequential Monte Carlo for inference · 1 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 FIVO with SIXO-q (single future observation)FIVO · Stochastic volatility modeltrain 4-particle bound: 6921.29 -> 6928.90Improved
replace FIVO with SIXO-DRE (all future observations)FIVO · Stochastic volatility modeltrain 4-particle bound: 6921.29 -> 6931.51Improved
replace FIVO with SIXO-DREFIVO · Stochastic volatility modeltrain BPF 2048-particle bound: 7020.14 -> 7019.42No clear effect
replace FIVO with SIXO-DREFIVO · Stochastic volatility modeltest BPF 2048-particle bound: 3352.71 -> 3354.27Improved
replace FIVO with SIXO-qFIVO · Stochastic volatility modeltest BPF 2048-particle bound: 3352.71 -> 3353.45Improved
replace FIVO with SIXOFIVO · Hodgkin-Huxley modeltest method 256-particle bound: -50.25 -> -47.94Improved
replace FIVO with SIXOFIVO · Hodgkin-Huxley modelrelative parameter error: 0.46 -> 0.02Improved
add gradient clipping to FIVOFIVO · Hodgkin-Huxley modelrelative parameter error: 0.46 -> 0.63Hurt
add gradient clipping to FIVOFIVO · Hodgkin-Huxley modeltest method 256-particle bound: -50.25 -> -51.43Hurt
use DRE-trained twists in SMC instead of bootstrap particle filterbootstrap particle filter · Hodgkin-Huxley synthetic datalog marginal lower bound: -74.89 -> -73.88Improved
use SIXO-u instead of FIVOFIVO · Gaussian drift diffusionbound gapImproved
use SIXO-DRE (biased lower-variance gradients) instead of SIXO-uSIXO-u · Gaussian drift diffusiongradient varianceImproved

Later papers that compared with this method

1 later accepted paper reports SIXO as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.

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