Overview | Puzzle Rules | Programmatic Play | Autoplay Strategies | Benchmarking | Local High Score

Play The Applet | Shiny Or Static HTML | Export A Local Copy

Campaign interface

Simulate a benchmark scenario | Benchmark multiple methods on shared truth | Run a repeated study | Run a targeted sensitivity study for FDA-aware SelectBoost | Inspect the saved larger study

Start here | Diagnostics and Validation | Benchmark Material | Minimal Orientation Example

Overview | Puzzle Rules | Programmatic Play | Autoplay Strategies | Benchmarking | Local High Score

Play The Applet | Shiny Or Static HTML | Export A Local Copy

2D Swarm Scenarios | Schooling 2D | Obstacle Corridor 2D | Predator Avoidance 2D

3D Swarm Scenarios | Murmuration 3D | Mixed Species 3D

Custom Corridor Workflow | Baseline Corridor | Stronger Avoidance Corridor

Swarm Art in the Browser | Boundary | Split Articles | Regeneration

Purpose | 2D Cumulative Trajectory | 3D Trajectory | Velocity and Direction Encodings | Exact Frame Samples | Shiny Timeline Integration | Limitations

Two Workflows | Applet: Grammar-style points and lines | Applet: Renderer-ready point specification | Coverage Summary | Core 2D Layers | Applet: Ordered 2D path with segments | Applet: Line sorting versus path order | Rectangles, Tiles, and Bins | Applet: Tile grid | Applet: Stacked bar counts | Applet: Histogram bins | Applet: Two-dimensional bins | Applet: Explicit rectangles | Curves and Contours

Boundary | Vector Arrows | Brush and Lasso Selection | Linked Magnifying-Glass Zoom | Timeline Controls | Opt-In 3D Camera | Mesh and Surface Helpers | Standalone Gallery

Experimental 3D, Mesh, and Surface Layers | Applet: 3D helix path | Applet: Structured surface | Applet: Unstructured mesh | 3D View and Camera Notes

Real-Data Lens | Example 1: Topographic Raster Field | Example 2: Observed Storm Trajectories | Example 3: Dense Real-World Embedding | Example 4: Fixed-Scale Faceted Panels | Real-Data Demo

Showcase Lens | Example 1: Latent-Space Population Structure | Example 2: Diffusion-Style Denoising Trajectories | Example 3: Nonlinear Phase Portrait | Example 4: Optimization Paths on a Surrogate Loss Landscape | Shiny Demo

Curves and Contours | Applet: Frequency polygons | Applet: Density curves | Code-only: Two-dimensional density contours | Code-only: Gridded contour lines | Ranges and Summaries | Applet: Linerange and pointrange | Applet: Error bars and crossbars | Applet: Boxplot summary | Applet: Violin density summary | Filled Regions | Applet: Ribbon band | Code-only: Area band | Applet: Simple polygon | Raster and Annotation Layers | Applet: Raster grid | Applet: Text and rug overlays | Code-only: Label overlay metadata | Facets, Coordinates, and Fallbacks | Code-only: Fixed-scale facets

Purpose | Structured Surface | Unstructured Mesh | Notes

Build a corridor experiment | Measure progress and clearance | Plot the world and final state | Sweep steering weights | Add a 3D mixed-species run

Helpers | Build example simulations | Compare the 3D examples | 2D variants | Animate with ggWebGL

Compare recorded swarms | Snapshot plots | Hand off to ggWebGL

Shared helpers | Foundational swarm-art recipes | Trail drawing | Time-layered particles | Negative-space obstacles | Depth as colour | Spectacular swarm-art examples | Nebula vortex | Predator comet | Obstacle bloom | Double helix ribbon | Exporting art | Design notes

Coverage Articles | Status Labels

Purpose | Metric Schema | Manual Dense Embedding Run | Scene-Type Metrics | Workflow Comparison | Interpreting Results

Boundary | Optional Dependency | Representative Scene | Multiscale Scene | Attribution Scene | Structure Scene | Regeneration

Create an xgeo_state | Compute backend state operators | Access backend-neutral fields | Build selected backend tables | Downstream consumers | Downstream use-case consumers | Write and reload state | Package boundary

Linear model: stats::lm() on mtcars | Logistic model: stats::glm() on mtcars | Clustering: stats::kmeans() on iris | Principal components: stats::prcomp() on USArrests | Regular-grid state: datasets::volcano | Backend-neutral exchange | Downstream handoff

Overview | Current capabilities | Example

Overview | Inspect the shipped iFlex example | Build daily segments | Fit forecasting models on the example panel | Run a small rolling benchmark | Inspect shipped benchmark results

Simulate a dataset | Add missingness and select components | Impute and re-fit | Real-data diagnostics | Study runners

Overview | Supported dataset matrix | Scaffolded, unshipped datasets | Shipped example panels | Shipped benchmark result datasets | Rebuilding the shipped artifacts | Example: daily segments from a shipped panel | Example: rerun a tiny benchmark locally

Scope | Overall summary | Correlated but not high-dimensional regimes | High-dimensional stress regime | Reproducing the study

Overview | Simulate a correlated design | Fit a first model | Summarize and extract stable support | Plot the frequency path | Formula interface and multiple quantiles | Inspect penalty tuning directly | Next steps

Build a design from a formula | Calibrate modeling choices | Compare methods on one design | Switch selector backends

Fit preprocessing from raw curves | Build a design with the fitted preprocessor | Fit grouped stability selection | Interpretation note

Build a functional design | Fit grouped stability selection | Interval-level summaries

Construct a spectral design object | Fit FDA-aware SelectBoost

Core Fitting Workflows | Linear PLS with matrix and formula interfaces | Generalized PLS models | Cross-Validation and Model Choice | Prediction and Missing Data | Bootstrap Utilities | Further Reading

What the Benchmark Helpers Do | Load the Package | Create a Benchmark Workspace | A Single Synthetic Benchmark Run | Validation Is Part of the Benchmark Workflow | External-Query Versus Self-Search Benchmarks | Benchmark a Recall Suite Across Parameter Grids | Optional Exact Recall Against bigKNN | Benchmark User-Supplied Data | Compare bigANNOY with Direct RcppAnnoy | Benchmark Scaling by Data Volume | Interpreting the Main Summary Columns | Installed Benchmark Runner | Recommended Workflow | Recap

The Core Difference | When To Use Which Package | Shared Result Shape | Load the Packages You Need | A Small Comparison Dataset | Approximate Search with bigANNOY | Exact Search with bigKNN When Available | What Does "Aligned Result Shape" Buy You? | Why bigANNOY Still Matters When bigKNN Exists | Benchmark Integration | A Practical Decision Framework | Important Boundaries | Recap

Load the Packages | Create a Small File-Backed Workspace | Build a File-Backed Reference Matrix | Build an Annoy Index from a Descriptor Path | Accepted File-Oriented Input Forms | Query with a File-Backed big.matrix | Query with a Descriptor Object and a Descriptor Path | Stream Results into File-Backed Destination Matrices | Reattach the Output Files Later | Separated-Column Query Matrices | Persisted Reference, Persisted Index, Persisted Outputs | Practical Tips | Recap

Load the Packages | Create a Small Reference Matrix | Build the First Annoy Index | Run a Self-Search | Search with an External Query Matrix | Tune the Main Search Controls | Stream Results into big.matrix Outputs | Reopen and Validate a Persisted Index | What Inputs Are Accepted? | Recap

Load the Packages | A Small Dataset for Metric Comparisons | Supported Metrics | Compare Metrics on the Same Queries | Build-Time Controls | n_trees | seed | build_threads | block_size | load_mode | Query-Time Controls | k | search_k | prefault | Use the Benchmark Helpers to Tune n_trees and search_k | Package-Level Defaults | A Practical Tuning Pattern | Recap

Why Lifecycle Management Matters | Load the Packages | Build an Index in Lazy Mode | Inspect the Sidecar Metadata | Lazy Loading Versus Eager Loading | Validate Without Loading | Validate and Load Explicitly | Close a Loaded Handle Explicitly | Reopen the Same Index in a New Object | Lifecycle State Lives in the Session Object | What Happens If Validation Fails? | Recommended Workflow | Recap

Load the Packages | Create a Small Persisted Example | What the Metadata Records | Validate Before You Use a Persisted Index | What Counts as an Error Versus a Warning | Reopen the Index as a Separate Session Object | Sharing Checklist | Simulate Sharing by Copying the Persisted Files | Non-Strict Validation for Diagnostics | Strict Validation as a Gate | A Common Sharing Pitfall: Renaming Only the .ann File | Recommended Sharing Pattern | Recap

Build a Small Reference Set | Directed k-NN graphs with knn_graph_bigmatrix() | Mutual k-NN graphs with mutual_knn_graph_bigmatrix() | Shared-nearest-neighbour graphs with snn_graph_bigmatrix() | Radius graphs with radius_graph_bigmatrix() | Symmetrization options and edge semantics | Converting outputs with as_edge_list(), as_triplet(), and as_sparse_matrix() | Using graph outputs downstream

Why plans and streaming matter for large matrices | Build a Repeatable Example | Building a plan with knn_plan_bigmatrix() | How memory budget maps to block size | Running planned in-memory search | Streaming k-NN output with knn_stream_bigmatrix() | Streaming radius output with radius_stream_bigmatrix() | Dense versus sparse query inputs | Practical guidance for choosing output modes

When prepared references help | Build a File-Backed Reference | Building a prepared reference with knn_prepare_bigmatrix() | Reusing it with knn_search_prepared() | Streaming prepared results with knn_search_stream_prepared() | Persisting caches with cache_path | Reloading with knn_load_prepared() | Validating with knn_validate_prepared() | Common failure modes and how to avoid them

Create a Small Reference Matrix | First Exact k-Nearest-Neighbour Search | Searching New Query Points | First Radius Search | Choosing a Metric | Where to Go Next

When resumable jobs are worth using | Build a Durable Working Directory | Checkpointed graph streaming with knn_graph_stream_bigmatrix() | Checkpointed radius streaming with radius_stream_job_bigmatrix() | Restarting work with resume_knn_job() | Graph Job Resume | Radius Job Resume | Destination matrix sizing and storage types | What checkpoint files contain | Failure recovery and restart patterns | Operational tips for long-running jobs

Why exact ground truth matters | Build a Small Exact Evaluation Set | Producing exact neighbours with bigKNN | Measuring recall with recall_against_exact() | Reranking candidate sets with rerank_candidates_bigmatrix() | Comparing approximate candidates against exact results | Suggested workflow alongside a separate ANN package | Interpreting recall and reranking results | Limits and caveats

Motivation | Theory | PLS Regression | PLS Generalized Linear Regression | Stopping Criteria | Bootstrap | Applications | Data | PLS Regression: Cornell | Bootstrap (y, X) | Bootstrap (y, T) | PLS Binary Logistic Regression: Microsatellites | Method and Results: Original Dataset | Specifying Families, Links, or Custom GLRs | Method and Results: Imputed Dataset | PLS Regression Bis: Pine Caterpillar | Bootstrap (y, X) and (y, T) | PLS Ordinal Logistic Regression: Bordeaux Wine Quality | PLS Ordinal Logistic Regression: Hyptis | PLS Poisson Regression: Rock | Creating Simulated Datasets | Simulating PLSR Datasets | Simulating Logistic Binary PLSGLR Datasets | Continuous Covariables | Dichotomous Only Covariables | Discussion | Core Object Classes | Core S3 Methods | Validation Examples | Main Features of the Package | Export Results to LaTeX | Session Information | References

Overview | How the benchmarks were produced | Focused comparison with irlba | Summary statistics | Visual comparison | Session information

Introduction | Supported estimators | Two complementary analysis paths | Comparison of estimators | Recommended default | Practical guidance

Context and non random case | Sobol and randomness I: random effect on output variable | Generate data | Three settings, two input variables | Sobol and randomness II: large random effect depending on an input variable | Sobol and randomness III: slight random effect depending on an input variable | Sobol and randomness IV: random variables with fixed distribution parameters

Model description | Simulation model | Sobol model wrapper | Sobol design for lambda and mu | Sobol indices | Summary

Introduction | Process model | Design for distributional parameters | Sobol indices based on a single trajectory | Sobol indices based on a quantity of interest | Qoi Mean | Qoi Median | Summary

Introduction | Deterministic Sobol g function | Order 1 and Total via sensitivity::sobol() | Order 1 and Total via sensitivity::sobol2007() | Random effect on the output | Quantity of interest based on repeated runs | Covariate dependent noise | Conclusion

Example data | Score plots with ellipses | Variable correlations and biplots | Bootstrap summaries

When does each win? | Sanity check | Overview | Why these choices? | The decision rule | Configuring the memory budget | Reproducibility knobs | Examples | References | Appendix: streaming Gram math

Overview | Benchmark design | Helper summaries | Example: PLS1, fixed size, varying components | Example: PLS2, fixed size, varying components | Short commentary

Overview | Simulated data | Internal benchmarks | External references | Takeaways

Overview | Recent additions | Simulated data | Internal benchmarks | External references | Key messages

Introduction | Baseline fit | (X, Y) bootstrap | (X, T) bootstrap | Exploring bootstrap scores | Parallel execution | Conclusion

Overview | Cross-validation | Information criteria | Parallel execution with future | Summary

Overview | Operator and Latent Directions | Centering for Prediction | Practical Notes | Minimal Example

Introduction | Benchmark design and data structure | PLS1: dense versus streaming | Fixed size, varying number of components | Relative speed and memory ratios | PLS2: multiple responses | Influence of the number of responses | Kernel and wide kernel PLS | Discussion and practical guidance

Notation | Pseudo-code for bigPLSR algorithms | SIMPLS (dense/bigmem) | NIPALS (dense/streamed) | Kernel PLS / RKHS (dense & streamed) | Double RKHS ( algorithm = "rkhs_xy" ) | Kalman-filter PLS (algorithm = "kf_pls") | Centering the Gram matrix | KLPLS / Kernel PLS (Dayal & MacGregor) | Streaming Gram blocks (column- and row-chunked) | Kernel approximations: Nyström and Random Fourier Features | Kernel Logistic PLS (binary classification) | Sparse Kernel PLS (sketch) | PLS in RKHS for X and Y (double RKHS) | Kalman-Filter PLS (KF-PLS; streaming) | API quick start | Prediction in RKHS PLS | Dependency overview (wrappers → C++ entry points) | References

Kernel Logistic PLS (klogitpls)

Idea | API | Notes

Overview | Dense example | Streaming example | Logistic response

Overview | Math sketch | APIs | When to prefer each variant | References

Motivation | Dependencies | Simulated data | Running the benchmark | Dense matrix comparison | Big-memory comparison | Visualising the results | Exporting benchmark tables | Additional scripts

Introduction | Simulating a large survival dataset | Dense-matrix solvers | Switching to file-backed matrices | Gradient descent for streaming data | Comparing the latent subspaces | Predictions on new data | Timing snapshot | Cleaning up backing files | Cleaning up | Further resources

Why bigPLScox? | Loading the example data | Inspecting deviance residuals | Matrix-based PLS–Cox models | Cross-validation | Fast solvers for medium-sized data | Fast PLS Cox vs gradient based PLS Cox | Predictions and evaluation | DK-splines extension | Next steps

Introduction | Simulated data | Running sb_beta() | Comparing selectors | Interval responses

Overview | Manual SelectBoost workflow with beta selectors | Running the entire loop with sb_beta() | Conference communications

Overview | Interval-generation parameters | Inspecting the simulated outcomes | Visualising interval widths | Point-response selectors on pseudo-observations | Visual comparisons | Interval stability selection with fastboost_interval | Interval SelectBoost with sb_beta_interval

Motivation | Building blocks | Pseudo-code: manual workflow | Pseudo-code: correlation grid driver | Extending the algorithms | Conference communications

What you'll learn | 1. Zero-inflated counts — pscl::bioChemists (ZIP/ZINB) | ZINB often handles overdispersion better than ZIP | Side-by-side metrics (ZIP vs ZINB) | 2. Semicontinuous (ZAGA) — airquality::Ozone | Effect plot for Temp on mu (ZAGA) | 3. Longitudinal growth with random effects — nlme::Orthodont

Overview | What you'll learn | Stability selection core (sb_gamlss) | SelectBoost correlated resampling (sb_prepare_selectboost) | Aggregating correlated draws (SelectBoost::boost.apply) | c0 grids and AutoBoost wrappers | Lightweight variants and tuning utilities | Confidence summaries

What you'll learn

What you'll learn | Confidence Functionals (AUSC, Coverage, Quantiles, Weighted, Conservative) | Grouped penalties for factors & splines | Tuning & Group Knockoffs

What you'll learn

What you'll learn

What you'll learn | Wide family sweep (auto) | Wide family sweep with skip reasons

What you'll learn | 1. Growth data (BCT) — Dutch boys | 2. Count data (PO) — Insurance claims | 3. Positive continuous (GA) — Old Faithful | 4. Binary (BI) — mtcars transmission | 5. Overdispersed counts (NBII) — quine absences | Tips

What you'll learn | Grouped penalties and parameter-specific engines | SelectBoost integrations: c0 grids, autoboost, and fastboost | Confidence summaries and effect diagnostics | Tuning engines and penalties | Fast deviance utilities and diagnostics | Parallel bootstraps, progress, and long tests

Overview | Filling and combining vectors | Dot products and element-wise operations | Reduction helpers

Overview | QR factorisation with dgeqrf() | Cholesky factorisation with dpotrf() | Eigenvalues and eigenvectors via dgeev() | Singular value decomposition with dgesdd()

Overview | Symmetric matrix products with dsymm() | General matrix multiplication with dgemm() | Updating matrices with daxpy()

Overview | Creating in-memory big.matrix objects | Working with file-backed matrices | Sharing matrices between sessions | Cleaning up backing files

Introduction | Preparing a big.matrix | Running PCA with bigPCAcpp | Comparing against prcomp | Variable relationships | Visualising PCA results | Singular value decomposition helpers | Robust PCA and SVD | Next steps for larger data

Installation | Table des matières | Statistics for Economics and Management (English version) | Contents

Abstract | Keywords | Introduction | PLS Beta Regression | Beta Regression | PLS Regression | Proposition | Bootstrap techniques, cross-validation and software implementation | Bootstrap techniques | Strengths of the software implementation | Selecting the number of components | Example of application in medicine | Example of application in chemometrics | Conclusion and perspectives | Acknowledgements

mi4p: multiple imputation for proteomics | Installation | Examples | First section | AMPUTATION | IMPUTATION | ESTIMATION | PROJECTION | MODERATED T-TEST

Patterns: a modeling tool dedicated to biological network modeling | Installation | Examples | Data management | Gene selection | Data simulation | Network inferrence | Perform gene selection

Data preparation | Selection genes according to their profiles. | Network inference | Focus on transcription factors.

Overview | Pine real dataset: pls and spls regressions | Loading and displaying dataset | PLS LOO and CV | PLS (Y,T) Bootstrap | sPLS (Y,T) Bootstrap | Bootstrap (Y,X) for the coefficients with number of components updated for each resampling | Aze real dataset: binary logistic plsRglm and sgpls regressions | PLSGLR (Y,T) Bootstrap | sparse PLSGLR (Y,T) Bootstrap

Introduction | Design approach and structure of the solution | Robust factor analysis | Conclusions

Introduction and Motivation | About tester

Introduction and Motivation | Indexification

Abstract | Overview | Generation of a network topology | Examples and checks | Details about the algorithm | Running the ABC algorithm | The simpliest way | Using ABC algorithm with full options