Machine learning discovers a tube-seeding strategy for IBP reduction of Feynman integrals that scales linearly with numerator power, demonstrated on rank-20 2-loop 5-point integrals.
hub
CMA-ES/pycma on Github
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
hub tools
citation-role summary
method 3
citation-polarity summary
verdicts
UNVERDICTED 14roles
method 3polarities
use method 3representative citing papers
Battery-Sim-Agent reframes inverse battery parameter estimation as an LLM reasoning task in closed loop with a simulator and outperforms Bayesian optimization baselines on diverse benchmarks.
A new three-point inverse solution using the α-β model reconstructs meteoroid masses and bulk densities from limited fireball observations, achieving 88% convergence on the EN catalog and producing a continuous density range of 300-4000 kg m^{-3} instead of discrete PE categories.
Reformulates constrained black-box optimization as posterior inference in latent space of flow-based models amortized by outsourced diffusion models, claiming superior performance on synthetic and real tasks.
Introduces observation traveling salesman distance and observation entropy to quantify exploration in Bayesian optimization acquisition functions and links them to empirical performance.
MSC-CMA-ES makes CMA-ES restarts structure-aware via cyclic nearest-better basin discovery on Sobol pre-samples, achieving 2.7x higher target coverage than BIPOP-CMA-ES on composition functions across CEC suites.
A trajectory optimization method performs geometry-aware updates in function space via natural functional gradients and Monte-Carlo estimation on a smoothed surrogate objective to improve feasibility and smoothness in robotic manipulation.
GraViti introduces a graph-level VAE with relaxed permutation invariance that maps whole graphs to latent vectors, achieves strong reconstruction on large molecular datasets, and generates valid samples by learning constraints directly from graph-level representations.
PhDLspec combines differential spectra from physical stellar models with a transformer to derive approximately 30 stellar parameters from low-resolution spectra hundreds of times faster than traditional calculations.
BAxUS adapts Bayesian optimization over nested random subspaces to achieve better performance than prior high-dimensional methods while providing theoretical guarantees against failure.
An empirical study of JEPA world models identifies architecture, training objective, and planning choices that yield a model outperforming DINO-WM and V-JEPA-2-AC on navigation and manipulation tasks.
A method combining goal babbling with CMA-ES-based local online motor babbling is used to learn inverse kinematics and explore motor abundance on a 10-DoF musculoskeletal robot arm.
Empirical benchmarking shows tolfunhist and the full portfolio stop CMA-ES closest to the optimal evaluation count on BBOB, while tolfun and tolfunhist often trigger before full stagnation.
Shallow MLPs and dense CPGs outperform deeper MLPs and Actor-Critic RL in bounded robot control tasks with limited proprioception, with a Parameter Impact metric indicating extra RL parameters yield no performance gain over evolutionary strategies.
citing papers explorer
-
Efficient AI-Inspired Reduction of Feynman Integrals via Tube Seeding
Machine learning discovers a tube-seeding strategy for IBP reduction of Feynman integrals that scales linearly with numerator power, demonstrated on rank-20 2-loop 5-point integrals.
-
Battery-Sim-Agent: Leveraging LLM-Agent for Inverse Battery Parameter Estimation
Battery-Sim-Agent reframes inverse battery parameter estimation as an LLM reasoning task in closed loop with a simulator and outperforms Bayesian optimization baselines on diverse benchmarks.
-
Consistency between dynamical modeling and photometrically derived masses of fireballs
A new three-point inverse solution using the α-β model reconstructs meteoroid masses and bulk densities from limited fireball observations, achieving 88% convergence on the EN catalog and producing a continuous density range of 300-4000 kg m^{-3} instead of discrete PE categories.
-
MSC-CMA-ES: Structure-Aware Restarts for CMA-ES via Cyclic Nearest-Better Basin Discovery
MSC-CMA-ES makes CMA-ES restarts structure-aware via cyclic nearest-better basin discovery on Sobol pre-samples, achieving 2.7x higher target coverage than BIPOP-CMA-ES on composition functions across CEC suites.
-
Natural Functional Gradients for Smooth Trajectory Optimization
A trajectory optimization method performs geometry-aware updates in function space via natural functional gradients and Monte-Carlo estimation on a smoothed surrogate objective to improve feasibility and smoothness in robotic manipulation.
-
GraViti: Graph-Level Variational Autoencoders with Relaxed Permutation Invariance
GraViti introduces a graph-level VAE with relaxed permutation invariance that maps whole graphs to latent vectors, achieves strong reconstruction on large molecular datasets, and generates valid samples by learning constraints directly from graph-level representations.
-
PhDLspec: physical-prior embedded deep learning method for spectroscopic determination of stellar labels in high-dimensional parameter space
PhDLspec combines differential spectra from physical stellar models with a transformer to derive approximately 30 stellar parameters from low-resolution spectra hundreds of times faster than traditional calculations.
-
Quantitative Performance Analysis of Stopping Criteria for CMA-ES
Empirical benchmarking shows tolfunhist and the full portfolio stop CMA-ES closest to the optimal evaluation count on BBOB, while tolfun and tolfunhist often trigger before full stagnation.
-
Benefits of Low-Cost Bio-Inspiration in the Age of Overparametrization
Shallow MLPs and dense CPGs outperform deeper MLPs and Actor-Critic RL in bounded robot control tasks with limited proprioception, with a Parameter Impact metric indicating extra RL parameters yield no performance gain over evolutionary strategies.