Description

weight ~ diam1 + diam2 + canopy.height + total.height + density + group

References: Gelman and Hill (2006)

Pair plot

Diagonal entries show estimates of the marginal densities as well as the (0.16, 0.5, 0.84) quantiles (dotted lines). Off-diagonal entries show estimates of the pairwise densities.

🔍 Full page 🔗 Info

Trace plots

🔍 Full page

Moments

parametersmeanstdmcseess_bulkess_tailrhatess_per_sec
beta.1-726.191153.7971.4101312017.114701.61.00008missing
beta.2189.619116.7051.248048848.359990.231.00011missing
beta.3372.171128.7031.405258418.169466.761.00015missing
beta.4354.382215.082.0692510915.412098.01.00004missing
beta.5-103.197191.2031.8885410360.311762.70.999997missing
beta.6131.31835.9370.3244312371.217406.71.00016missing
beta.7-362.838104.8031.0152510901.412229.21.00021missing
sigma277.80832.87360.15641947061.663446.71.00001missing
💾 CSV

Cumulative traces

For each iteration $i$, shows the running average up to $i$, $\frac{1}{i} \sum_{n = 1}^{i} x_n$.

🔍 Full page

Local communication barrier

When the global communication barrier is large, many chains may be required to obtain tempered restarts.

The local communication barrier can be used to visualize the cause of a high global communication barrier. For example, if there is a sharp peak close to a reference constructed from the prior, it may be useful to switch to a variational approximation.

🔍 Full page 🔗 Info

GCB estimation progress

Estimate of the Global Communication Barrier (GCB) as a function of the adaptation round.

The global communication barrier can be used to set the number of chains. The theoretical framework of Syed et al., 2021 yields that under simplifying assumptions, it is optimal to set the number of chains (the argument n_chains in pigeons()) to roughly 2Λ.

Last round estimate: $1.8925687935135764$

🔍 Full page 🔗 Info

Evidence estimation progress

Estimate of the log normalization (computed using the stepping stone estimator) as a function of the adaptation round.

Last round estimate: $-277.7681892745702$

🔍 Full page 🔗 Info

Round trips

Number of tempered restarts as a function of the adaptation round.

A tempered restart happens when a sample from the reference percolates to the target. When the reference supports iid sampling, tempered restarts can enable large jumps in the state space.

🔍 Full page 🔗 Info

Pigeons summary

roundn_scansn_tempered_restartsglobal_barrierglobal_barrier_variationallast_round_max_timelast_round_max_allocationstepping_stone
1205.68434e-14missing0.6239315.12512e72.84217e-14
2402.84217e-14missing1.069395.29653e71.42109e-14
3802.84217e-14missing0.070759892336.00.0
41644.9738e-14missing0.184018160528.02.84217e-14
532125.32907e-14missing0.191157234720.03.77476e-15
664284.26326e-14missing0.373494397120.0-1.02141e-14
7128604.69624e-14missing0.681869734352.06.66134e-15
82561243.57492e-14missing1.577951.35826e61.33227e-15
95122526.03961e-14missing2.847562.6708e61.33227e-15
1010245086.92779e-14missing6.007455.21402e61.77636e-15
11204810205.16254e-14missing11.15021.04888e7-8.88178e-16
12409620445.29576e-14missing22.22772.06258e71.77636e-15
13819240926.59472e-14missing45.06154.16857e7-8.88178e-16
141638481887.10543e-14missing90.0138.22844e70.0
1532768163801.33116e-13missing179.2651.66549e81.77636e-15
166553658691.70904missing301.4562.60924e10-277.563
17131072150651.89257missing602.3065.23031e10-277.768
💾 CSV🔗 Info

Pigeons inputs

KeysValues
extended_tracesfalse
checked_round0
extractornothing
recordFunction[Pigeons.traces, Pigeons.round_trip, Pigeons.log_sum_ratio, Pigeons.timing_extrema, Pigeons.allocation_extrema]
multithreadedfalse
show_reporttrue
n_chains10
variationalGaussianReference(Dict{Symbol, Any}(), Dict{Symbol, Any}(), 15)
explorernothing
n_chains_variational0
targetStanLogPotential(mesquite_model)
n_rounds17
exec_folder/scratch/st-alexbou-1/abc/InferHub-infra/work/de/6b56923933f2d25613fd49419c4122/results/all/2024-05-16-15-56-20-2j5xhh1T
referencenothing
checkpointtrue
seed1
💾 CSV🔗 Info