SMC Inner kernel tuning

[ciguaran]

• Tunes the parameters of the inner kernel (mutation) inside SMC, based on the output of the previous step (state and sampling info).
  See Design choice (c) of section 2.1.3 from https://arxiv.org/abs/1808.07730.
• Implements some tuning:

1. inverse mass matrix from particles (useful for HMC)
2. mean, std and covariance from particles (useful for IRMH)
3. scale based on acceptance rate

See sampling-notebook PR: blackjax-devs/sampling-book#49

Previously discussed here: #245

A few important guidelines and requirements before we can merge your PR:

• [Y] If I add a new sampler, there is an issue discussing it already;
• [Y] We should be able to understand what the PR does from its title only;
• [Y] There is a high-level description of the changes;
• [Y] There are links to all the relevant issues, discussions and PRs;
• [Y ] The branch is rebased on the latest main commit;
• [Y] Commit messages follow these guidelines;
• [Y] The code respects the current naming conventions;
• [Y] Docstrings follow the numpy style guide
• [Y] pre-commit is installed and configured on your machine, and you ran it before opening the PR;
• [Y] There are tests covering the changes;
• [Y] The doc is up-to-date;
• [Y] If I add a new sampler* I added/updated related examples

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Comparison is base (0a84b22) 99.16% compared to head (ab46961) 99.18%.

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #595      +/-   ##
==========================================
+ Coverage   99.16%   99.18%   +0.01%     
==========================================
  Files          54       57       +3     
  Lines        2513     2563      +50     
==========================================
+ Hits         2492     2542      +50     
  Misses         21       21              

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[junpenglao]

Great work! Only minor comments.

[junpenglao]

Great work! Last bit of nitpick :-)