Gpytorch

What's Changed
* `main` and `develop` branches by gpleiss in https://github.com/cornellius-gp/gpytorch/pull/2542
* Include jaxtyping to allow for Tensor/LinearOperator typehints with sizes. by gpleiss in https://github.com/cornellius-gp/gpytorch/pull/2543
* fix: replace deprecated scipy.integrate.cumtrapz with cumulative_trapezoid by natsukium in https://github.com/cornellius-gp/gpytorch/pull/2545
* use common notation for normal distribution N(\mu, \sigma^2) by partev in https://github.com/cornellius-gp/gpytorch/pull/2547
* fix broken link in Simple_GP_Regression.ipynb by partev in https://github.com/cornellius-gp/gpytorch/pull/2546
* Deprecate last_dim_is_batch (bump PyTorch version to >= 2.0) by gpleiss in https://github.com/cornellius-gp/gpytorch/pull/2549
* Added ability for priors of transformed distributions to have their p… by hvarfner in https://github.com/cornellius-gp/gpytorch/pull/2551
* Avoid unnecessary memory allocation for covariance downdate in SGPR prediction strategy by JonathanWenger in https://github.com/cornellius-gp/gpytorch/pull/2559
* Fix VNNGP with batches by LuhuanWu in https://github.com/cornellius-gp/gpytorch/pull/2375
* fix a typo by partev in https://github.com/cornellius-gp/gpytorch/pull/2570
* fix a typo by partev in https://github.com/cornellius-gp/gpytorch/pull/2571
* DOC: improve the formatting in the documentation by partev in https://github.com/cornellius-gp/gpytorch/pull/2578

New Contributors
* natsukium made their first contribution in https://github.com/cornellius-gp/gpytorch/pull/2545
* hvarfner made their first contribution in https://github.com/cornellius-gp/gpytorch/pull/2551

**Full Changelog**: https://github.com/cornellius-gp/gpytorch/compare/v1.12...v1.13

What's Changed
* Minor patch to Matern covariances by j-wilson in https://github.com/cornellius-gp/gpytorch/pull/2378
* Fix error messages for ApproximateGP.get_fantasy_model by gpleiss in https://github.com/cornellius-gp/gpytorch/pull/2374
* Fix lazy kernel slicing when there are multiple outputs by douglas-boubert in https://github.com/cornellius-gp/gpytorch/pull/2376
* Fix training status of noise model of `HeteroskedasticNoise` after exceptions by fjzzq2002 in https://github.com/cornellius-gp/gpytorch/pull/2382
* Stop rbf_kernel_grad and rbf_kernel_gradgrad creating the full covariance matrix unnecessarily by douglas-boubert in https://github.com/cornellius-gp/gpytorch/pull/2388
* Likelihood bugfix by gpleiss in https://github.com/cornellius-gp/gpytorch/pull/2395
* Update RTD configuration, and linear_operator requirement. by gpleiss in https://github.com/cornellius-gp/gpytorch/pull/2399
* Better support for missing labels by Turakar in https://github.com/cornellius-gp/gpytorch/pull/2288
* Fix latex of gradients in docs by jlperla in https://github.com/cornellius-gp/gpytorch/pull/2404
* Skip the warning in `gpytorch.lazy.__getattr__` if name starts with `_` by saitcakmak in https://github.com/cornellius-gp/gpytorch/pull/2423
* Fix KeOps regressions from 2296. by gpleiss in https://github.com/cornellius-gp/gpytorch/pull/2413
* Update index.rst by mkomod in https://github.com/cornellius-gp/gpytorch/pull/2449
* `python` should also be a runtime dependency by jaimergp in https://github.com/cornellius-gp/gpytorch/pull/2457
* fix a typo: cannonical -> canonical by partev in https://github.com/cornellius-gp/gpytorch/pull/2461
* Update distributions.rst by chrisyeh96 in https://github.com/cornellius-gp/gpytorch/pull/2487
* Fix flaky SVGP classification test by gpleiss in https://github.com/cornellius-gp/gpytorch/pull/2495
* DOC: Fix typo in docstring. by johanneskopton in https://github.com/cornellius-gp/gpytorch/pull/2493
* fix a typo by partev in https://github.com/cornellius-gp/gpytorch/pull/2464
* DOC: fix formatting issue in RFFKernel documentation by partev in https://github.com/cornellius-gp/gpytorch/pull/2463
* DOC: fix broken formatting in leave_one_out_pseudo_likelihood.py by partev in https://github.com/cornellius-gp/gpytorch/pull/2462
* `ConstantKernel` by SebastianAment in https://github.com/cornellius-gp/gpytorch/pull/2511
* DOC: fix broken URL in periodic_kernel.py by partev in https://github.com/cornellius-gp/gpytorch/pull/2513
* Bug: Exploit Structure in get_fantasy_strategy by naefjo in https://github.com/cornellius-gp/gpytorch/pull/2494
* Matern52 grad by m-julian in https://github.com/cornellius-gp/gpytorch/pull/2512
* Added optional `kwargs` to `ExactMarginalLogLikelihood` call by rafaol in https://github.com/cornellius-gp/gpytorch/pull/2522
* Corrected configuration of ``exclude`` statements in ``pre-commit`` configuration by JonathanWenger in https://github.com/cornellius-gp/gpytorch/pull/2541

New Contributors
* douglas-boubert made their first contribution in https://github.com/cornellius-gp/gpytorch/pull/2376
* fjzzq2002 made their first contribution in https://github.com/cornellius-gp/gpytorch/pull/2382
* jlperla made their first contribution in https://github.com/cornellius-gp/gpytorch/pull/2404
* mkomod made their first contribution in https://github.com/cornellius-gp/gpytorch/pull/2449
* jaimergp made their first contribution in https://github.com/cornellius-gp/gpytorch/pull/2457
* partev made their first contribution in https://github.com/cornellius-gp/gpytorch/pull/2461
* chrisyeh96 made their first contribution in https://github.com/cornellius-gp/gpytorch/pull/2487
* johanneskopton made their first contribution in https://github.com/cornellius-gp/gpytorch/pull/2493
* naefjo made their first contribution in https://github.com/cornellius-gp/gpytorch/pull/2494
* rafaol made their first contribution in https://github.com/cornellius-gp/gpytorch/pull/2522

**Full Changelog**: https://github.com/cornellius-gp/gpytorch/compare/v1.11...v1.12

What's Changed
* Fix solve_triangular(Tensor, LinearOperator) not supported in VNNGP by Turakar in https://github.com/cornellius-gp/gpytorch/pull/2323
* Metrics fixes and cleanup by JonathanWenger in https://github.com/cornellius-gp/gpytorch/pull/2325
* Lock down doc requirements to prevent RTD failures. by gpleiss in https://github.com/cornellius-gp/gpytorch/pull/2339
* Fix typos in multivariate_normal.py by manuelhaussmann in https://github.com/cornellius-gp/gpytorch/pull/2331
* add Hamming IMQ kernel by samuelstanton in https://github.com/cornellius-gp/gpytorch/pull/2327
* Use torch.cdist for `dist` by esantorella in https://github.com/cornellius-gp/gpytorch/pull/2336
* Enable fantasy models for multitask GPs Reborn by yyexela in https://github.com/cornellius-gp/gpytorch/pull/2317
* Clean up deprecation warnings by saitcakmak in https://github.com/cornellius-gp/gpytorch/pull/2348
* More informative string representation of MultitaskMultivariateNormal distributions. by gpleiss in https://github.com/cornellius-gp/gpytorch/pull/2333
* Mean and kernel functions for first and second derivatives by ankushaggarwal in https://github.com/cornellius-gp/gpytorch/pull/2235
* Bugfix: double added log noise prior by LuisAugenstein in https://github.com/cornellius-gp/gpytorch/pull/2355
* Remove Module.__getattr__ by saitcakmak in https://github.com/cornellius-gp/gpytorch/pull/2359
* Remove num_outputs from IndependentModelList by saitcakmak in https://github.com/cornellius-gp/gpytorch/pull/2360
* keops periodic and keops kernels unit tests by m-julian in https://github.com/cornellius-gp/gpytorch/pull/2296
* Deprecate checkpointing by gpleiss in https://github.com/cornellius-gp/gpytorch/pull/2361

New Contributors
* Turakar made their first contribution in https://github.com/cornellius-gp/gpytorch/pull/2323
* manuelhaussmann made their first contribution in https://github.com/cornellius-gp/gpytorch/pull/2331
* esantorella made their first contribution in https://github.com/cornellius-gp/gpytorch/pull/2336
* yyexela made their first contribution in https://github.com/cornellius-gp/gpytorch/pull/2317
* ankushaggarwal made their first contribution in https://github.com/cornellius-gp/gpytorch/pull/2235
* LuisAugenstein made their first contribution in https://github.com/cornellius-gp/gpytorch/pull/2355

**Full Changelog**: https://github.com/cornellius-gp/gpytorch/compare/v1.10...v1.11

What's Changed
* Re-add pyro + torch_master check by gpleiss in https://github.com/cornellius-gp/gpytorch/pull/2241
* Fix silently ignored arguments in IndependentModelList by saitcakmak in https://github.com/cornellius-gp/gpytorch/pull/2249
* fix bug in nearest_neighbor_variational_strategy by LuhuanWu in https://github.com/cornellius-gp/gpytorch/pull/2243
* Move infinite interval bounds check into Interval constructor by Balandat in https://github.com/cornellius-gp/gpytorch/pull/2259
* Use ufmt for code formatting and import sorting by Balandat in https://github.com/cornellius-gp/gpytorch/pull/2262
* Update nearest_neighbors.py by yw5aj in https://github.com/cornellius-gp/gpytorch/pull/2267
* Use raw strings to avoid "DeprecationWarning: invalid escape sequence" by saitcakmak in https://github.com/cornellius-gp/gpytorch/pull/2282
* Fix handling of re-used priors by Balandat in https://github.com/cornellius-gp/gpytorch/pull/2269
* Fix BernoulliLikelihood documentation by gpleiss in https://github.com/cornellius-gp/gpytorch/pull/2285
* gpytorch.settings.variational_cholesky_jitter can be set dynamically. by gpleiss in https://github.com/cornellius-gp/gpytorch/pull/2255
* Likelihood docs update by gpleiss in https://github.com/cornellius-gp/gpytorch/pull/2292
* Improve development/contributing documentation by gpleiss in https://github.com/cornellius-gp/gpytorch/pull/2293
* Use raw strings to avoid "DeprecationWarning: invalid escape sequence" by saitcakmak in https://github.com/cornellius-gp/gpytorch/pull/2295
* Update SGPR notebook by gpleiss in https://github.com/cornellius-gp/gpytorch/pull/2303
* Update linear operator dependency to 0.4.0 by gpleiss in https://github.com/cornellius-gp/gpytorch/pull/2321

New Contributors
* yw5aj made their first contribution in https://github.com/cornellius-gp/gpytorch/pull/2267

**Full Changelog**: https://github.com/cornellius-gp/gpytorch/compare/v1.9.1...v1.10

What's Changed
* Fix LMCVariationalStrategy example in docs by adamjstewart in https://github.com/cornellius-gp/gpytorch/pull/2112
* Accept closure argument in NGD optimizer `step` by dannyfriar in https://github.com/cornellius-gp/gpytorch/pull/2118
* Fix bug with Multitask DeepGP predictive variances. by gpleiss in https://github.com/cornellius-gp/gpytorch/pull/2123
* Autogenerate parameter types in documentation from python typehints by gpleiss in https://github.com/cornellius-gp/gpytorch/pull/2125
* Retiring deprecated versions of`psd_safe_cholesky`, `NotPSDError`, and `assert_allclose` by SebastianAment in https://github.com/cornellius-gp/gpytorch/pull/2130
* fix custom dtype_value_context setting by sdaulton in https://github.com/cornellius-gp/gpytorch/pull/2132
* Include linear operator in installation instructions by saitcakmak in https://github.com/cornellius-gp/gpytorch/pull/2131
* Fixes HalfCauchyPrior by feynmanliang in https://github.com/cornellius-gp/gpytorch/pull/2137
* Fix return type of `Kernel.covar_dist` by Balandat in https://github.com/cornellius-gp/gpytorch/pull/2138
* Change variable name for better understanding by findoctorlin in https://github.com/cornellius-gp/gpytorch/pull/2135
* Expose jitter by hughsalimbeni in https://github.com/cornellius-gp/gpytorch/pull/2136
* Add HalfNormal prior distribution for non-negative variables. by ZitongZhou in https://github.com/cornellius-gp/gpytorch/pull/2147
* Fix multitask/added_loss_term bugs in SGPR regression by gpleiss in https://github.com/cornellius-gp/gpytorch/pull/2121
* fix bugs in test half Cauchy prior. by ZitongZhou in https://github.com/cornellius-gp/gpytorch/pull/2156
* Generalize RandomModule by feynmanliang in https://github.com/cornellius-gp/gpytorch/pull/2164
* MMVN.to_data_independent_dist returns correct variance for non-interleaved MMVN distributions. by gpleiss in https://github.com/cornellius-gp/gpytorch/pull/2172
* Update MSLL in metrics.py by jongwonKim-1997 in https://github.com/cornellius-gp/gpytorch/pull/2177
* Update multitask example notebook by gpleiss in https://github.com/cornellius-gp/gpytorch/pull/2190
* Fix exception message for missing kernel lazy kernel attribute by dannyfriar in https://github.com/cornellius-gp/gpytorch/pull/2195
* Improving `_sq_dist` when `x1_eq_x2` by SebastianAment in https://github.com/cornellius-gp/gpytorch/pull/2204
* Fix docs/requirements.txt by gpleiss in https://github.com/cornellius-gp/gpytorch/pull/2206
* As per issue '2175 [Docs] GP Regression With Uncertain Inputs'. by corwinjoy in https://github.com/cornellius-gp/gpytorch/pull/2200
* Avoid evaluating kernel when adding jitter by gpleiss in https://github.com/cornellius-gp/gpytorch/pull/2189
* Avoid evaluating kernel in `expand_batch` by dannyfriar in https://github.com/cornellius-gp/gpytorch/pull/2185
* Deprecating `postprocess` by SebastianAment in https://github.com/cornellius-gp/gpytorch/pull/2205
* Make PiecewisePolynomialKernel GPU compatible by gpleiss in https://github.com/cornellius-gp/gpytorch/pull/2217
* Let `LazyEvaluatedKernelTensor` recall the grad state at instantiation by SebastianAment in https://github.com/cornellius-gp/gpytorch/pull/2229
* Doc Update for Posterior Model Distribution and Posterior Predictive Distribution by varunagrawal in https://github.com/cornellius-gp/gpytorch/pull/2230
* Fix 08_Advanced_Usage links by st-- in https://github.com/cornellius-gp/gpytorch/pull/2240
* Add `device` property to `Kernel`s, add unit tests by Balandat in https://github.com/cornellius-gp/gpytorch/pull/2234
* pass **kwargs to ApproximateGP.__call__ in DeepGPLayer by IdanAchituve in https://github.com/cornellius-gp/gpytorch/pull/2224

New Contributors
* dannyfriar made their first contribution in https://github.com/cornellius-gp/gpytorch/pull/2118
* SebastianAment made their first contribution in https://github.com/cornellius-gp/gpytorch/pull/2130
* feynmanliang made their first contribution in https://github.com/cornellius-gp/gpytorch/pull/2137
* findoctorlin made their first contribution in https://github.com/cornellius-gp/gpytorch/pull/2135
* hughsalimbeni made their first contribution in https://github.com/cornellius-gp/gpytorch/pull/2136
* ZitongZhou made their first contribution in https://github.com/cornellius-gp/gpytorch/pull/2147
* jongwonKim-1997 made their first contribution in https://github.com/cornellius-gp/gpytorch/pull/2177
* corwinjoy made their first contribution in https://github.com/cornellius-gp/gpytorch/pull/2200
* varunagrawal made their first contribution in https://github.com/cornellius-gp/gpytorch/pull/2230
* st-- made their first contribution in https://github.com/cornellius-gp/gpytorch/pull/2240
* IdanAchituve made their first contribution in https://github.com/cornellius-gp/gpytorch/pull/2224

**Full Changelog**: https://github.com/cornellius-gp/gpytorch/compare/v1.9.0...v1.9.1

Starting with this release, the `LazyTensor` functionality of GPyTorch has been pulled out into its own separate Python package, called [linear_operator](https://github.com/cornellius-gp/linear_operator). Most users won't notice the difference (at the moment), but power users will notice a few changes.

If you have your own custom LazyTensor code, don't worry: this release is backwards compatible! However, you'll see a lot of annoying deprecation warnings 😄

LazyTensor -> LinearOperator
- All `gpytorch.lazy.*LazyTensor` classes now live in the `linear_operator` repo, and are now called `linear_operator.operator.*LinearOperator`.
- For example, `gpytorch.lazy.DiagLazyTensor` is now `linear_operator.operators.DiagLinearOperator`
- The only major naming change: `NonLazyTensor` is now `DenseLinearOperator`
- `gpytorch.lazify` and `gpytorch.delazify` are now `linear_operator.to_linear_operator` and `linear_operator.to_dense`, respectively.
- The `_quad_form_derivative` method has been renamed to `_bilinear_derivative` (a more accurate name!)
- `LinearOperator` method names now reflect their corresponding PyTorch names. This includes:
- `add_diag` -> `add_diagonal`
- `diag` -> `diagonal`
- `inv_matmul` -> `solve`
- `symeig` -> `eigh` and `eigvalsh`
- `LinearOperator` now has the `mT` property

__torch_function__ functionality

LinearOperators are now compatible with the torch api! For example, the following code works:

python
diag_linear_op = linear_operator.operators.DiagLinearOperator(torch.randn(10))
torch.matmul(diag_linear_op, torch.randn(10, 2)) returns a torch.Tensor!


Other files that have moved:

- `gpytorch.functions` - all of the core functions used by LazyTensors now live in the LinearOperator repo. This includes: diagonalization, dsmm, inv_quad, inv_quad_logdet, matmul, pivoted_cholesky, root_decomposition, solve (formally inv_matmul), and sqrt_inv_matmul
- `gpytorch.utils` - a few have moved to the LinearOperator repo. This includes: broadcasting, cholesky, contour_intergral_quad, getitem, interpolation, lanczos, linear_cg, minres, permutation, stable_pinverse, qr, sparse, SothcasticLQ, and toeplitz.

**Full Changelog**: https://github.com/cornellius-gp/gpytorch/compare/v1.8.1...v1.9.0