deep_ritz_stochastic_quadrature_sampling
Generate stochastic interior and boundary quadrature samples for Deep Ritz variational PDE training.
- License 许可
- Apache-2.0
- 最近更新
- 2026-09-03
- Stars
- ★ 351
- Forks
- 27
01 前言 Front Matter
- name
- deep_ritz_stochastic_quadrature_sampling
- description
- Generate stochastic interior and boundary quadrature samples for Deep Ritz variational PDE training.
02 资源文件 2
- 脚本scripts/sampler.py1.9 KB
- 脚本tests/test_sampler.py903 B
03 SKILL.md 正文
Deep Ritz Stochastic Quadrature Sampling
When To Use
Use this skill when implementing a Deep Ritz or variational neural PDE experiment that needs Monte Carlo estimates of domain and boundary integrals. Do not use it for fixed-grid finite differences or finite elements.
Inputs
dimension: positive integer spatial dimension.lower,upper: scalar hypercube bounds.interior_count: number of interior samples.boundary_count: number of boundary samples.seed: optional deterministic seed.
Outputs
- Interior points inside
[lower, upper]^dimension. - Boundary points with at least one coordinate fixed to a lower or upper face.
- Face metadata for each boundary point.
Workflow
- Use fresh random interior points for each training iteration.
- Sample boundary faces uniformly across dimensions and low/high sides.
- Use simple batch means as equal-weight Monte Carlo quadrature estimates.
- Use fixed seeds only for validation, tests, and reproducible reduced recovery.
Validation
Run:
python tests/test_sampler.py
Limitations
The helper targets hypercube domains, matching the paper's high-dimensional Poisson recovery. L-shaped domains require a custom rejection sampler.
04 同仓库更多 Skills
passnet-triton-opt
Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block/grid/warp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.
passnet-solve
END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.
passnet-skill
PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under ./pass_dir/, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.
passnet-pattern-fusion
Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()/replacement_args()/replacement_func() files, when a pass "failed to match", or when deciding how to fuse multiple kernels/ops.
passnet-orchestrate
Round/batch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep/revert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.
passnet-feedback
Fast, deterministic feedback for PassNet work: pre-flight pattern/match verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).