All authors
Claude Skills by VectorSpaceLab
github.com/VectorSpaceLab6,028 skills13 installs7,823 views
- Scaled Lbfgs SolverRun bounded scaled L-BFGS optimization with two-loop directions, memory updates, and backtracking safeguards.Votes: 0GitHub stars: 247
- Two Loop DirectionCompute L-BFGS search directions with the two-loop inverse-Hessian recursion and scalar scaling.Votes: 0GitHub stars: 247
- Adaptive Ntk WeightingCompute Algorithm 1 PINN loss weights from NTK trace ratios with degeneracy checks and diagnostics.Votes: 0GitHub stars: 247
- Ntk Block SpectrumCompute PINN neural tangent kernel block traces, eigenvalue summaries, and dominance diagnostics from empirical Jacobians.Votes: 0GitHub stars: 247
- Pinn Residual ProblemBuild deterministic PINN residual problem fixtures with boundary and PDE residual targets for NTK recovery experiments.Votes: 0GitHub stars: 247
- Proxy Training RecoveryRun bounded proxy PINN training comparisons that exercise residual construction, NTK weighting, and optimizer updates.Votes: 0GitHub stars: 247
- Autodiff Pde ResidualCompute Burgers-style PINN residual values and derivative diagnostics from differentiable or analytic surrogate predictions.Votes: 0GitHub stars: 247
- Pde Problem SpecificationDefine auditable PINN PDE recovery items with separate observations, collocation points, coefficients, provenance, and target metadata.Votes: 0GitHub stars: 247
- Pinn Recovery EvaluationConvert PINN traces into numeric proxy metrics and mechanism checks for validator-ready recovery evidence.Votes: 0GitHub stars: 247
- Pinn Training ObjectiveCombine PINN supervised and residual losses and execute bounded optimizer updates with validator-compatible traces.Votes: 0GitHub stars: 247
- Architecture Curvature ComparisonCompares curvature metrics across architecture-style variants and records qualitative sharper/flatter conclusions.Votes: 0GitHub stars: 247
- Hessian Vector ProtocolDefines model, loss, parameter, gradient, and Hessian-vector product contracts for PyHessian-style curvature analysis.Votes: 0GitHub stars: 247
- Reduced Recovery EvaluationPackages reduced recovery evidence, source-boundary checks, mechanism checks, metrics, and validation-ready logs.Votes: 0GitHub stars: 247
- Spectral Density SlqBuilds a Lanczos tridiagonal matrix from HVP calls and extracts eigenvalue-weight pairs as a compact ESD proxy.Votes: 0GitHub stars: 247
- Top Eigen Trace EstimatorsImplements power iteration and Hutchinson trace estimation over an HVP oracle for fast curvature summaries.Votes: 0GitHub stars: 247
- Nystrom Pcg SolverSolve regularized PSD systems with randomized Nyström preconditioned conjugate gradients and log convergence evidence.Votes: 0GitHub stars: 247
- Nystrom PreconditionerBuild and apply the inverse action of the Nyström preconditioner for regularized PSD linear systems.Votes: 0GitHub stars: 247
- Randomized Nystrom FactorizationCompute a stable randomized Nyström PSD low-rank eigendecomposition from a dense PSD matrix or matrix-vector product interface.Votes: 0GitHub stars: 247
- Rank And Recovery EvaluationCompute effective dimension, choose a bounded Nyström rank, and evaluate recovery traces for condition-number and PCG iteration improvements.Votes: 0GitHub stars: 247
- Go Explore Archive Selection UpdateMaintain and sample Go-Explore archive entries using score, length, and exploration metadata.Votes: 0GitHub stars: 247
- Go Explore Cell RepresentationBuild stable Go-Explore archive cell keys from structured or grid observations for bounded recovery experiments.Votes: 0GitHub stars: 247
- Go Explore Return Then Explore LoopExecute a bounded Go-Explore return-then-explore Phase 1 loop in resettable sparse-reward environments.Votes: 0GitHub stars: 247
- Go Explore Robustification EvaluationEvaluate Go-Explore archived trajectories with deterministic replay and bounded perturbation checks for recovery evidence.Votes: 0GitHub stars: 247
- Axiom Recovery EvaluationEvaluate Integrated Gradients experiments against completeness, sensitivity, implementation invariance, and symmetry axioms.Votes: 0GitHub stars: 247
- Baseline Path ProtocolBuild and validate absence baselines and straight-line interpolation paths for Integrated Gradients recovery experiments.Votes: 0GitHub stars: 247
- Integrated Gradient ComputationCompute Integrated Gradients with Riemann-summed path gradients and completeness diagnostics for attribution recovery.Votes: 0GitHub stars: 247
- Jsrl Guide Policy ContractValidate a Jump-Start Reinforcement Learning guide-policy interface and better-than-random progress assumptions before using it for roll-in.Votes: 0GitHub stars: 247
- Jsrl Recovery EvaluationEvaluate Jump-Start Reinforcement Learning recovery evidence with mechanism checks for guide roll-in, curriculum handoff, value update, and proxy metric validity.Votes: 0GitHub stars: 247
- Jsrl Switching Rollout CurriculumBuild Jump-Start Reinforcement Learning rollouts that switch from guide-policy control to exploration-policy control under curriculum or random guide-step schedules.Votes: 0GitHub stars: 247
- Jsrl Value Exploration UpdateApply a minimal value-based exploration-policy update to Jump-Start Reinforcement Learning trajectories and record optimizer evidence.Votes: 0GitHub stars: 247
- Ppo Actor Critic Update LoopExecute a reduced PPO actor-critic update with clipped surrogate, value loss, and optimizer-step evidence.Votes: 0GitHub stars: 247
- Ppo Clipped Surrogate ObjectiveCompute and validate PPO clipped probability-ratio surrogate objectives and trust-region-style diagnostics.Votes: 0GitHub stars: 247
- Ppo Recovery Evaluation HarnessValidate reduced PPO recovery evidence with mechanism checks, source-boundary checks, and pass-rate metrics.Votes: 0GitHub stars: 247
- Ppo Rollout Advantage ProtocolCompute PPO fixed-segment rollout returns and generalized advantage estimates with auditable terminal handling.Votes: 0GitHub stars: 247
- Rnd Bonus ModelCompute Random Network Distillation novelty bonuses from frozen deterministic target features and trainable predictor mean-squared error.Votes: 0GitHub stars: 247
- Rnd Dual Value Return CombinationCompute separate extrinsic and intrinsic return streams for Random Network Distillation dual-value-head policy optimization.Votes: 0GitHub stars: 247
- Rnd Intrinsic Reward ScalingScale Random Network Distillation intrinsic rewards with running discounted-return statistics for stable exploration bonuses.Votes: 0GitHub stars: 247
- Rnd Observation NormalizationNormalize observations for Random Network Distillation with running statistics and clipping before target and predictor feature computation.Votes: 0GitHub stars: 247
- Rnd Proxy Recovery HarnessRun a bounded Random Network Distillation proxy recovery experiment with executable evidence and generated-skill invocation logs.Votes: 0GitHub stars: 247
- Sac Max Entropy ObjectiveCompute Soft Actor-Critic maximum-entropy value and actor objective terms for bounded recovery experiments.Votes: 0GitHub stars: 247
- Sac Off Policy ReplayBuild and sample validated off-policy replay batches for Soft Actor-Critic recovery harnesses.Votes: 0GitHub stars: 247
- Sac Recovery EvaluationScore reduced Soft Actor-Critic recovery traces for mechanism fidelity and source boundary compliance.Votes: 0GitHub stars: 247
- Sac Update StepExecute one deterministic reduced Soft Actor-Critic critic actor and target update for recovery evidence.Votes: 0GitHub stars: 247
- Actor Critic Sil IntegrationRun a bounded actor-critic Self-Imitation Learning update and log trainable parameter evidence.Votes: 0GitHub stars: 247
- Positive Advantage Sil LossCompute Self-Imitation Learning policy and value losses using the paper's positive-advantage gate.Votes: 0GitHub stars: 247
- Sil Recovery EvaluationValidate Self-Imitation Learning recovery evidence for source boundaries, executable metrics, and mechanism-faithful proxy checks.Votes: 0GitHub stars: 247
- Trajectory Return ReplayBuild Self-Imitation Learning replay records by converting completed agent episodes into discounted state-action-return tuples.Votes: 0GitHub stars: 247
- Qos Local SearchAllocate high-priority traffic first and iteratively increase low-priority shaper rates while residual estimated capacity permits objective improvement.Votes: 0GitHub stars: 247
- Sabe EstimatorEstimate overlay load and safe available bandwidth from existing delay or packet-loss measurements using M/M/1/K equations.Votes: 0GitHub stars: 247
- Sdwan Flow ModelRepresent flow groups, overlay links, priorities, SLA thresholds, and per-flow measurements for QoS optimization experiments.Votes: 0GitHub stars: 247