← Back
Home › Systems › Frontier AI research

materials-discovery

ML materials discovery

GNoME

SystemTechniques · 12Primitives · 53 materials-discovery Backfill schedulingdistributed · medium: Run small jobs in gaps ahead of reserved large jobs without delaying themDAG workflow executiondistributed · medium: Run a graph of dependent tasks by releasing each one when its inputs are done, longest chain first, and skip any task whose input hashes are unchanged.›Convex hull quickhullgeometry · medium: Quickhull in 2D and 3D: robust convex hulls for collision shapes and geometryActive learningmachine-learning · medium: Choosing which unlabeled examples to label next: uncertainty, margin, diversity and committee samplingGraph neural networksmachine-learning · medium: Message-passing neural networks over graphs (GCN, GAT, equivariant) for molecules and relationsSe3 equivariant networksmachine-learning · medium: Networks equivariant to rotations and translations (invariant point attention, EGNN)Genetic algorithmsoptimization · medium: Population search with selection, crossover and mutation for black-box optimizationCalibrationmachine-learning · low: Make predicted probabilities match observed frequencies: measure with ECE, fix post hoc with temperature, Platt or isotonic scaling on held-out data.›Verlet / leapfrognumerics · low: Half-kick, drift, half-kick: a second-order, time-reversible, symplectic integrator with one force evaluation per step whose energy error stays bounded for millions of steps.›Periodic boundary conditionsphysics · low: Minimum image convention and wrapping for simulations in periodic boxesSymmetry data augmentationmachine-learning · low: Augment board-game training data with the board's symmetry group (8 dihedral transforms)Diffusion modelsml-training · low: Train a network to undo Gaussian noise at every noise level, then generate by integrating from pure noise to data; the standard for images, video and audio.›Mixed-precision trainingml-training · low: Run matmuls in bf16/fp16/fp8 on tensor cores while keeping master weights, optimizer state and reductions in fp32; about 2x speed, half the activation memory.›L-BFGSnumerics · low: Quasi-Newton minimizer that approximates the inverse Hessian from the last m gradient differences via the two-loop recursion; O(m·n) memory and work per step.›Neighbor listsphysics · low: Cell lists plus Verlet buffer lists for O(n) short-range pair interactionsInterval treedata-structures · low: Index of ranges that answers "which intervals overlap this point or range?" in O(log n + k); static sorted-array form is the compact, cache-friendly choice.›Topological sortgraphs · low: Order the vertices of a DAG so every edge points forward; the core of build systems, schedulers and dependency resolution, with cycle detection for free.›Content-addressed storagestorage · low: Store each blob under the hash of its bytes: immutable, deduplicated by construction, self-verifying on every read, and composable into Merkle trees.›Exponential backoff with jittersystems · low: Retry after delays that grow geometrically and are randomized, so failed clients spread out instead of hammering a recovering service in synchronized waves.›Exact geometric predicatesgeometry · low: Robust orient and incircle tests with adaptive-precision floats (Shewchuk) or exact arithmeticFloating-point errornumerics · low: How IEEE 754 rounding error accumulates and how to contain it: compensated (Kahan/Neumaier) and pairwise summation, error-free transformations with FMA, ULP comparisons.›Embeddingsmachine-learning · low: A learned table mapping discrete ids to dense vectors: gather forward, sparse scatter-add backward, row-wise optimizers to keep huge tables cheap.›k-means clusteringmachine-learning · low: Partition points into k clusters by alternating nearest-centroid assignment and centroid averaging; k-means++ seeding makes it dependable.›+ 5 more techniques+ 37 more primitives

Similar systems

Share the most building blocks with this one.

quantum-chemistry 20 %