AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

Continuous-depth Deep Gaussian Processes

Ying Li, Sanyou Wu, Zi Yang, Qiaochu Xu, YUHAO LIU, Zhidi Lin, Michael Minyi Zhang, Petar Djuric, alexandre thiery

NeurIPS 2026 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Infinite-width networks as Gaussian processes · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes continuous-depth deep Gaussian processes in which the latent representation evolves as a stochastic differential equation over a continuous depth variable, rather than a discrete stack of GP layers.

Problem

Standard discrete-depth deep Gaussian processes become harder to optimize as depth increases.

Approach

Treat depth as a latent continuous evolution: the latent representation follows a stochastic differential equation with a depth-indexed dynamic, replacing a long discrete stack of GP layers.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add residual (identity) connections to plain DGP (ablation)DGP · benchmark regression (6 datasets)RMSE/NLL: NLL 1.442 -> 1.254 on heteroscedasticImproved
increase discrete depth L from 1 to 10 in plain DGP (ablation)DGP · Toy regressionRMSE, NLL, MAEHurt
increase discrete depth L in residual DGP (ablation)Residual DGP · Toy regressionRMSE, NLL, MAEMixed
vary discretization steps J from 1 to 10 (ablation)CDGP · Toy regressionRMSE, NLL, MAENo clear effect
vary terminal depth T from 1 to 10 (ablation)CDGP · Toy regressionRMSE, NLL, MAENo clear effect
use GP prior over drift instead of neural drift (NSDE)continuous-depth SDE · benchmark regression (6 datasets)NLL: NLL 3.527 -> 1.285 (heteroscedastic, NSDE vs CDGP)Improved
evolve base drift with a CNF (FlowDGP) instead of direct separable GP prior (CDGP)CDGP · benchmark regression (6 datasets)train time (s): 201.330 -> 27.490 on heavy_tailedImproved
replace CDGP with FlowDGPCDGP · heteroscedastic, nonstationaryNLL: 1.285 -> 1.248; 0.979 -> 0.411Improved
use FlowDGP instead of CDGPCDGP · sarcos_smallNLL: 0.376 -> 1.352Hurt
use continuous-depth models instead of TGPTGP · 6 benchmark datasetsRMSEImproved
use FlowDGP instead of NSDE on large-scale uci_bikeNSDE · uci_bike (full)RMSE, NLL, CRPSImproved
use FlowDGP instead of NSDE on large-scale uci_energyNSDE · uci_energy (full)NLLHurt

Experimental setup

Builds on: deep Gaussian processes neural ODE

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