RAYEN: Imposition of Hard Convex Constraints on Neural Networks
Overview
This research presents RAYEN, a framework for enforcing hard convex constraints on neural network outputs or latent variables. Unlike prior methods that rely on soft constraints or iterative corrections, RAYEN guarantees constraint satisfaction at all times with minimal computational overhead (e.g., 8 ms for 1K quadratic constraints). The authors validate the approach on learned locomotion policies for a quadruped robot in both simulation and real-world experiments, demonstrating speedups of 20 to 7468 times over state-of-the-art algorithms while maintaining near-optimal costs. Source code is available at https://github.com/leggedrobotics/rayen.
Generated from attributed reports · Updated 2 days ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · overhead_time_ms: 8 other · Basis not reported · Differing source assertions
“ear matrix inequality (LMI) constraints, with negligible overhead compared to unconstrained networks. For instance, it imposes 1K quadratic constraints on a 1K-dimensional variable with only 8 ms of overhead compared to a network that does not enforce these constraints. An LMI constraint with 300x300 dense matrices on a 10K-dimensional variable can be guaranteed with only 12 ms additional overhead. When used in neura”
Exact source · revision 1Source owner not reported
Reported quantity · overhead_time_ms: 12 other · Basis not reported · Differing source assertions
“ear matrix inequality (LMI) constraints, with negligible overhead compared to unconstrained networks. For instance, it imposes 1K quadratic constraints on a 1K-dimensional variable with only 8 ms of overhead compared to a network that does not enforce these constraints. An LMI constraint with 300x300 dense matrices on a 10K-dimensional variable can be guaranteed with only 12 ms additional overhead. When used in neura”
Exact source · revision 1Source owner not reported
Reported quantity · speedup_factor_min: 20 other · Basis not reported
“l networks that approximate the solution of constrained trajectory optimization problems, RAYEN runs 20 to 7468 times faster than state-of-the-art algorithms, while guaranteeing constraint satisfaction at all times and achieving a near-optimal cost. Finally, we demonstrate RAYEN's ability to enforce actuator constraints on a learned locomotion policy by validating constraint satisfaction in both simulation and real-w”
Exact source · revision 1Source owner not reported
Reported quantity · speedup_factor_max: 20 other · Basis not reported
“l networks that approximate the solution of constrained trajectory optimization problems, RAYEN runs 20 to 7468 times faster than state-of-the-art algorithms, while guaranteeing constraint satisfaction at all times and achieving a near-optimal cost. Finally, we demonstrate RAYEN's ability to enforce actuator constraints on a learned locomotion policy by validating constraint satisfaction in both simulation and real-w”
Exact source · revision 1Source owner not reported
Reported quantity · constraint_count: 1000 other · Basis not reported
“ear matrix inequality (LMI) constraints, with negligible overhead compared to unconstrained networks. For instance, it imposes 1K quadratic constraints on a 1K-dimensional variable with only 8 ms of overhead compared to a network that does not enforce these constraints. An LMI constraint with 300x300 dense matrices on a 10K-dimensional variable can be guaranteed with only 12 ms additional overhead. When used in neura”
Exact source · revision 1Source owner not reported
Reported quantity · variable_dimension: 1000 other · Basis not reported
“ear matrix inequality (LMI) constraints, with negligible overhead compared to unconstrained networks. For instance, it imposes 1K quadratic constraints on a 1K-dimensional variable with only 8 ms of overhead compared to a network that does not enforce these constraints. An LMI constraint with 300x300 dense matrices on a 10K-dimensional variable can be guaranteed with only 12 ms additional overhead. When used in neura”
Exact source · revision 1Source owner not reported
Reported quantity · matrix_size_rows: 300 other · Basis not reported
“ear matrix inequality (LMI) constraints, with negligible overhead compared to unconstrained networks. For instance, it imposes 1K quadratic constraints on a 1K-dimensional variable with only 8 ms of overhead compared to a network that does not enforce these constraints. An LMI constraint with 300x300 dense matrices on a 10K-dimensional variable can be guaranteed with only 12 ms additional overhead. When used in neura”
Exact source · revision 1Source owner not reported
Reported quantity · matrix_size_cols: 300 other · Basis not reported
“ear matrix inequality (LMI) constraints, with negligible overhead compared to unconstrained networks. For instance, it imposes 1K quadratic constraints on a 1K-dimensional variable with only 8 ms of overhead compared to a network that does not enforce these constraints. An LMI constraint with 300x300 dense matrices on a 10K-dimensional variable can be guaranteed with only 12 ms additional overhead. When used in neura”
Exact source · revision 1Source owner not reported
Artifact availability · code: available
“orld experiments on a quadruped robot. The code is available at https://github.com/leggedrobotics/rayen”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalRAYEN: Imposition of Hard Convex Constraints on Neural Networks
This research presents RAYEN, a framework for enforcing hard convex constraints on neural network outputs or latent variables. Unlike prior methods that rely on soft constraints or iterative corrections, RAYEN guarantees constraint satisfaction at all times with minimal computational overhead (e.g., 8 ms for 1K quadratic constraints). The authors validate the approach on learned locomotion policies for a quadruped robot in both simulation and real-world experiments, demonstrating speedups of 20 to 7468 times over state-of-the-art algorithms while maintaining near-optimal costs. Source code is available at https://github.com/leggedrobotics/rayen.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).