Naive approach for IID potential evaluation for score estimators

[Kartik-Sama]

Addresses the issue #1450

Used Effective Sample Score (ESS) to evaluate the log_probs returned by estimated posterior. This way log_probs are being checked both for single observation and iid observations case through the test added via the parameter - iid_batch_size

[codecov]

Codecov Report

❌ Patch coverage is 75.00000% with 6 lines in your changes missing coverage. Please review.
✅ Project coverage is 83.73%. Comparing base (19364f0) to head (8296538).
⚠️ Report is 2 commits behind head on main.

Files with missing lines	Patch %	Lines
sbi/inference/potentials/vector_field_potential.py	70.00%	6 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #1508      +/-   ##
==========================================
- Coverage   86.70%   83.73%   -2.98%     
==========================================
  Files         134      134              
  Lines       11151    11168      +17     
==========================================
- Hits         9669     9352     -317     
- Misses       1482     1816     +334     

Flag	Coverage Δ
unittests	83.73% <75.00%> (-2.98%)	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

Files with missing lines	Coverage Δ
sbi/inference/posteriors/vector_field_posterior.py	71.53% <100.00%> (-7.58%)	⬇️
sbi/inference/potentials/vector_field_potential.py	74.10% <70.00%> (-13.65%)	⬇️

... and 30 files with indirect coverage changes

[manuelgloeckler]

Thanks for implementing looks great.

Just a few changes i.e. moving the tests and using corresponding pytest fixture needs to be done.

[manuelgloeckler]

Thanks, great effort. Looks good.

This is done, but I will block merging this for now as it will have conflicts with #1497.

[manuelgloeckler]

Alright this can finally be merged. Will update based on the current main and then see if everything still works.

[Copilot]

Pull Request Overview

This PR implements IID (Independent and Identically Distributed) potential evaluation for score estimators, addressing issue #1450. The implementation uses Effective Sample Score (ESS) to evaluate log_probs for both single observations and IID observations cases.

Key Changes

• Added IID support to vector field potential evaluation by implementing multiple flows for batch processing
• Introduced log probability computation for IID observations with proper mathematical adjustments
• Added comprehensive test coverage for IID functionality with parameterized batch sizes

Reviewed Changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 2 comments.

File	Description
sbi/inference/potentials/vector_field_potential.py	Implements IID potential evaluation with flow rebuilding and log probability computation
sbi/inference/posteriors/vector_field_posterior.py	Updates log_prob method to detect and handle IID observations
tests/linearGaussian_vector_field_test.py	Adds parameterized test for IID log probability computation

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}