RLNS regularizes LNS to perform block Gibbs sampling under entropy, interpolating between pseudolikelihood and exact MLE for differentiable combinatorial optimization.
The elements of differentiable program- ming
9 Pith papers cite this work, alongside 7 external citations. Polarity classification is still indexing.
9
Pith papers citing it
7
external citations · external index
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
A framework learns constitutive priors from noisy data to enable PDE-constrained inverse design of elastic networks using latent variables, homotopy continuation, Chamfer distance matching, and neural smoothness constraints.
A hybrid Jeffreys+baseline prior removes multi-σ prior-volume projection in DESI DR1 full-shape fits of H0, w0, and wa, yielding late-time expansion constraints consistent with HOD-informed Bayesian and frequentist analyses.
A differentiable-physics solver reconstructed wall shear stress accurately from limited passive-scalar data in 2D and 3D flow benchmarks, outperforming physics-informed neural networks in most scenarios.
AD-MPCC integrates differentiable MPCC, online Pacejka parameter estimation via moving-horizon methods, and a supervised ML model to adapt objective weights, yielding safer and faster simulated laps on varying surfaces.
DIFFRACT develops a duality theory for standard interference functions to unroll iterative algorithms into differentiable neural architectures for end-to-end learning in wireless resource management.
Under the chain rule of probability, autoregressive models and energy-based models are in exact bijection in function space, making the global optimum of teacher forcing equivalent to an energy-based model with implicit lookahead.
A feedback optimization pipeline for tri-level mobility games outperforms Bayesian optimization and genetic algorithms on Zurich multimodal data while identifying incentives that boost multimodal use.
This perspective paper categorizes hybrid architectures for combining mechanistic and data-driven models using residual learning, Neural ODEs, and solver-in-the-loop to model neurological disorder progression.
citing papers explorer
-
Regularized Large Neighborhood Search
RLNS regularizes LNS to perform block Gibbs sampling under entropy, interpolating between pseudolikelihood and exact MLE for differentiable combinatorial optimization.
-
Constitutive Priors for Inverse Design
A framework learns constitutive priors from noisy data to enable PDE-constrained inverse design of elastic networks using latent variables, homotopy continuation, Chamfer distance matching, and neural smoothness constraints.
-
Alleviating prior dependencies for DESI DR1 clustering fits through reparameterization
A hybrid Jeffreys+baseline prior removes multi-σ prior-volume projection in DESI DR1 full-shape fits of H0, w0, and wa, yielding late-time expansion constraints consistent with HOD-informed Bayesian and frequentist analyses.
-
Wall Shear Stress Reconstruction from Concentration: Differentiable Physics and Physics-Informed Neural Networks
A differentiable-physics solver reconstructed wall shear stress accurately from limited passive-scalar data in 2D and 3D flow benchmarks, outperforming physics-informed neural networks in most scenarios.
-
AD-MPCC: Adaptive Differentiable Model Predictive Contouring Control for Autonomous Racing
AD-MPCC integrates differentiable MPCC, online Pacejka parameter estimation via moving-horizon methods, and a supervised ML model to adapt objective weights, yielding safer and faster simulated laps on varying surfaces.
-
DIFFRACT: Neuralized Utility Maximization for Wireless Networks by Differentiable Programming
DIFFRACT develops a duality theory for standard interference functions to unroll iterative algorithms into differentiable neural architectures for end-to-end learning in wireless resource management.
-
Autoregressive Language Models are Secretly Energy-Based Models: Insights into the Lookahead Capabilities of Next-Token Prediction
Under the chain rule of probability, autoregressive models and energy-based models are in exact bijection in function space, making the global optimum of teacher forcing equivalent to an energy-based model with implicit lookahead.
-
Hierarchical Strategic Decision-Making in Layered Mobility Systems
A feedback optimization pipeline for tri-level mobility games outperforms Bayesian optimization and genetic algorithms on Zurich multimodal data while identifying incentives that boost multimodal use.
-
Integrating Mechanistic and Data-Driven Models for Neurological Disorders through Differentiable Programming
This perspective paper categorizes hybrid architectures for combining mechanistic and data-driven models using residual learning, Neural ODEs, and solver-in-the-loop to model neurological disorder progression.