v0.25.0

✨ Highlights

🚀 New Inference Methods

• MNPE class mixed parameter (similar to MNLE) by @dgedon in #1362
• Implementation of SNPE-B (#199) by @etouron1 in #1471

🧠 Neural Network Architectures & Embedding Networks

• Add transformer embedding net by @NicolasRR in #1494
• Add embedding net that uses 1D causal convolutions (#1459) by @Aranka-S in #1499
• Add LRU-backed embedding networks by @famura in #1512
• Add ResNet as embedding model by @StefanWahl in #1472
• Spectral convolution embedding net by @L-in-da in #1503

⭐ Major Features & Capabilities

• Unify flow matching and score-based models by @StarostinV in #1497
• Model misspecification detection based on MMD by @coschroeder in #1502
• Marginal estimator log-prob based test for misspecification by @swag2198 in #1522
• Adding interface for unconditional flow training by @plcrodrigues in #1470
• Support using trained estimators in Pyro models by @sethaxen in #1491
• Add util to generate mcmc samples from user defined potential (#1405) by @hayden-johnson in #1483
• Logit transform by @anastasiakrouglova in #1485
• Log-prob for iid data for score estimators by @Kartik-Sama in #1508

📚 Documentation & Tutorials

• Tutorial on new features for score-based methods #1392 by @touronc in #1489
• Docs: Introduce Readthedocs website by @michaeldeistler in #1463

🐛 Bug Fixes

• z_score correct order in Zuko by @anastasiakrouglova in #1492
• Minor fix when moving thetas from GPU to CPU by @famura in #1515
• Minor fix while using unconditional density estimator and LRU embedding by @ARna06 in #1556
• fix: replace 'in' operator with '==' for proper classifier comparison by @abelaba in #1550
• flowmatching condition shape fix by @gmoss13 in #1584
• patch for torch bug in tarp, run torch.histogram with cpu-only tensor by @psteinb in #1596
• fix failing tarp test by @janfb in #1628
• fix: cap max_sampling_batch_size to prevent excessive memory by @janfb in #1624
• 1561 computation of denoising posterior precision matrix in jac method score fn iid by @manuelgloeckler in #1636
• fix xfail test, fix deprecation warnings by @janfb in #1642
• fix: iid-score device handling by @janfb in #1650
• fix: fmpe singularity on sde sampling by @manuelgloeckler in #1661

🛠️ Maintenance & Improvements

🔧 Code Quality & Refactoring

• Refactoring flow and score matching classes and nets by @manuelgloeckler in #1544
• Rename inference trainer classes by @abelaba in #1605
• Rename VectorFieldInference to VectorFieldTrainer by @abelaba in #1614
• Refactor build_posterior to Eliminate Duplication Across Trainers by @abelaba in #1610
• Refactor build posterior method arguments to use Literals by @abelaba in #1606
• Refactor build_posterior Posterior Configuration Using Dataclasses by @abelaba in #1619
• Use TypeAlias and consistent naming for sbi types by @janfb in #1637
• Add protocol for estimator builder by @abelaba in #1633
• Improve abc implementation by @janfb in #1615
• Refactor RatioEstimator to subclass ConditionalEstimator @abelaba in #1652

🏷️ Type Hints & API Improvements

• fix: add enum for flow options to fix type hints. by @janfb in #1562
• fix LC2ST kwarg typing by @janfb in #1565
• fix: Update RatioEstimator classifier argument to use a Protocol by @abelaba in #1582
• Update append_simulations return type to Self by @abelaba in #1622
• Deprecation Warnings for build_posterior stringly typed parameters by @abelaba in #1627

🧪 Testing & CI/CD

• Testmon by @manuelgloeckler in #1452
• disable testmon for now by @manuelgloeckler in #1467
• chore: Use pytest-split plugin in ci workflow by @schroedk in #1465
• tests: refactor "not slow" tests to be not so slow by @janfb in #1495
• Test for known pytorch distribution transform issue by @dgedon in #1504
• xfail scan test on python 3.13 by @manuelgloeckler in #1533
• Gpu test for VectorFieldPosterior by @jorobledo in #1542
• set vector field iid-tests xfail by @janfb in #1554
• Changed the xfail condition for LRU tests with mode='scan' by @famura in #1552
• Fix/lru test by @Matthijspals in #1568
• refactor sbc funcs and tests by @janfb in #1578
• chore: remove testmon, add codecov test analytics by @janfb in #1592
• chore: reorder setup steps for Python and uv in CI/CD workflows by @janfb in #1601
• Fix/lc2st numpy type fixes by @janfb in #1613
• Fix failing CI on main. by @janfb in #1618
• Fix slow vector field tests by @janfb in #1657
• Add tests for sensitivity analysis by @janfb in #1662

📖 Documentation & Website

• Fix tests for new docs by @michaeldeistler in #1475
• Prevent notebook execution upon doc build by @michaeldeistler in #1477
• Fix broken links on website by @michaeldeistler in #1480
• fix: Update documentation folder path by @abelaba in #1510
• fix path to contribute.md by @psteinb in #1507
• Add utils to docs by @sethaxen in #1520
• Update new Readthedocs website by @michaeldeistler in #1519
• fix broken links on new website by @michaeldeistler in #1538
• Fixups for new website landing page by @michaeldeistler in #1539
• Fix: add tutorial page to mkdocs website by @michaeldeistler in #1540
• Fix broken links in some tutorials by @michaeldeistler in #1541
• Add examples to documentation by @jorobledo in #1548
• docs: Add importance_sampling_parameters to build_posterior docstring. by @abelaba in #1558
• Add missing arguments to LikelihoodEstimator and RatioEstimator docstrings. by @abelaba in #1571
• Fixups for new RTD website by @michaeldeistler in #1573
• Tutorial with a more representative training loop by @michaeldeistler in #1574
• Fixups for rendering of HH tutorial notebook by @michaeldeistler in #1575
• fix for colors in Hodgkin-Huxley notebook by @michaeldeistler in #1576
• Add citations to how-to guide by @michaeldeistler in #1579
• Clarify fullscreen view of applications-explorer by @michaeldeistler in #1580
• Fixups for the documentation by @michaeldeistler in #1585
• fixed misrendered bullet list, tested locally by @psteinb in #1594
• Improvements to L-C2ST tutorial by @michaeldeistler in #1588
• docs: Change colortheme in light mode by @michaeldeistler in #1638
• Posterior parameters doc by @abelaba in #1644
• fix contributing links by @janfb in #1647
• docs: add posterior parameters dataclass how to guide by @abelaba in #1654

🏗️ Infrastructure & Dependencies

• Add uv support by @abelaba in #1518
• switch to numfocus code of conduct by @janfb in #1560
• Update readme with new JOSS citation by @janfb in #1564
• update numfocus code of conduct by @janfb in #1602
• Added Apache License reference comments to source files + CI bash script check by @nMaax in #1599

👥 User Experience & Warnings

• Change xfail to skipif as outcome is not consistent by @gmoss13 in #1487
• Add warning when using append_simulations with exclude_invalid_x=True by @abelaba in #1486
• Batch sampling slow without warning by @dgedon in #1490
• Clarify pbar annotation in sample_batched for DirectPosterior by @StefanWahl in #1493

🎮 GPU Support & Device Handling

• Prior to(device) by @jorobledo in #1505
• posterior.to(device) by @jorobledo in #1527

🔧 Miscellaneous Improvements

• ref: update tests, add types and docs to marginal trainer by @janfb in #1516
• integrate sbi application eplorer by @lappalainenj in #1567
• fix: update notebook references by @emmanuel-ferdman in #1563
• Update sbiutils.py to use one-dimensional batch by @vivienr in #1577
• fix: remove empty list default argument by @abelaba in #1608
• fix: throw exception on unsupported activation function by @emmanuel-ferdman in #1609
• fix: resolve logger warnings by @emmanuel-ferdman in #1598
• fix paths by @manuelgloeckler in #1641

🎉 New Contributors

• @abelaba made their first contribution in #1486
• @dgedon made their first contribution in #1490
• @StefanWahl made their first contribution in #1493
• @touronc made their first contribution in #1489
• @jorobledo made their first contribution in #1505
• @hayden-johnson made their first contribution in #1483
• @sethaxen made their first contribution in #1491
• @etouron1 made their first contribution in #1471
• @Aranka-S made their first contribution in #1499
• @swag2198 made their first contribution in #1522
• @StarostinV made their first contribution in #1497
• @L-in-da made their first contribution in #1503
• @NicolasRR made their first contribution in #1494
• @vivienr made their first contribution in #1577

Full Changelog: v0.24.0...v0.25.0