Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

4468911,3371,782 · Jun 202019922001200920172026
48 results for differentiable structure learning

Proposes a differentiable structure learning framework for general binary data.

problem Limitations of existing methods in discrete data structure learning.
method Formulates a differentiable optimization task for arbitrary dependencies in general discrete models.
result Establishes identifiability of complete set of compatible parameters and structures under mild assumptions.

New method recovers transportable DAG structures from different datasets.

problem Inference of DAG structures is computationally expensive and lacks transportability.
method Introduces D-Struct, a differentiable architecture that recovers transportable DAG structures.
result D-Struct recovers transportable DAG structures from different datasets.

New method resolves inconsistency in learning directed acyclic graphs using penalized likelihood.

problem Inconsistency of 1\ell_1-penalized likelihood in learning directed acyclic graphs.
method Developed a hybrid differentiable structure learning method based on 0\ell_0-penalized likelihood with hard acyclicity constraint.
result Demonstrated and explained why 1\ell_1-penalized likelihood is fundamentally inconsistent in identifying true structure up to Markov equivalence classes.

Differentiable structure learning addresses DAGs with multiple global minimizers.

problem Identify the true DAG from global minimizers of acyclicity-constrained optimization problems.
method Carefully regularize the likelihood to identify the sparsest model in the Markov equivalence class.
result Regularization of the likelihood defines a score that identifies the sparsest model in general models and likelihoods.

Privacy constraints affect learning Markov Random Fields differently.

problem Learning Markov Random Fields under differential privacy constraints.
method Algorithms for structure and parameter learning under pure, concentrated, and approximate differential privacy.
result Privacy constraints impose a strong separation between structure and parameter learning in high-dimensional data.

A novel method for learning Bayesian network structures from decentralized data, balancing privacy and efficiency.

problem Privacy and communication costs in learning Bayesian network structures from decentralized data.
method Fed-Sparse-BNSL, combining differential privacy with greedy updates targeting only a few relevant edges per participant.
result Achieves utility close to non-private baselines while offering stronger privacy and communication efficiency.

The paper explores deep learning through algebra and geometry, highlighting geometric structures and differential processes.

problem Understanding the geometric and algebraic foundations of deep learning.
method Investigates neural networks from perceptron to transformer, emphasizing geometric structures and differential processes.
result A coordinate-free formulation of backpropagation equations using canonical scalar products on matrix spaces.

SCOTCH learns system structure from irregular time series using neural SDEs.

problem Learning system structure from irregular time series data.
method SCOTCH uses neural stochastic differential equations (SDE) with variational inference.
result SCOTCH improves structure learning performance on synthetic and real-world datasets.

Paper establishes convergence rates for learning elliptic pseudo-differential operators.

problem Learning elliptic pseudo-differential operators in partial differential equations.
method Wavelet-Galerkin framework, structured infinite-dimensional regression problem, sparse estimator, matrix compression, nested-support strategy.
result Obtained convergence rates for the estimator and efficient Galerkin solver.

Paper develops a consistent algorithm for learning graph structure from continuous-time stochastic differential equations.

problem Learning structure from continuous-time stochastic differential equations.
method Score-based structure learning using Neural Ordinary Differential Equations with adaptive regularization.
result The method consistently recovers directed graphs of local independencies in systems of stochastic differential equations.

Develops experimental design for discovering missing physics in bioreactors.

problem Discovering missing physics in incomplete model structures of process systems.
method Combines universal differential equations and symbolic regression with sequential experimental design.
result Successfully recovered true model structure of a bioreactor using machine learning techniques.

The closure conditions of the inexact exterior differential form and dual form (an equality to zero of differentials of these forms) can be treated as a definition of some differential-geometrical structure. Such a connection discloses the properties and specific features of the differential-geometrical structures. The…

2004-04-12abs ↗pdf ↗

Deep NLP models benefit from underlying structures in the data---e.g., parse trees---typically extracted using off-the-shelf parsers. Recent attempts to jointly learn the latent structure encounter a tradeoff: either make factorization assumptions that limit expressiveness, or sacrifice end-to-end differentiability. Us…

2018-09-03abs ↗pdf ↗

CASPER improves DAG structure learning by integrating graph structure into score function.

problem Discovering suboptimal DAGs and model vulnerabilities in causal discovery.
method CASPER integrates graph structure into the score function as a new measure in the causal space, enhancing DAG structure learning via adaptive attention to DAG-ness.
result CASPER outperforms state-of-the-art methods in terms of accuracy and robustness.

Differentiable causal discovery methods perform robustly under model violations.

problem Causal discovery algorithms struggle with real-world data due to unverifiable causal assumptions.
method Benchmarked differentiable causal discovery methods under eight model assumption violations.
result Differentiable causal discovery methods exhibit robust performance under Structural Hamming Distance and Structural Intervention Distance metrics.

Differentiable perturbed optimizers enable end-to-end learning of discrete decisions.

problem Discrete decisions in machine learning pipelines break back-propagation.
method Transform optimizers into differentiable operations using stochastically perturbed optimizers.
result Smoothness of derivatives can be tuned via noise amplitude.

A new method for differentiable structured sparsity improves neural network performance and sparsity.

problem Non-differentiability of structured sparsity penalties in neural networks.
method Introducing DD-Gating, a differentiable approach to structured overparameterization.
result The DD-Gating objective converges to the L2,2/DL_{2,2/D}-regularized loss and induces sparse learning dynamics.

NDM incorporates geometric structure into neural networks for better optimization and interpretability.

problem Efficient and interpretable deep learning architectures.
method NDM is a neural network architecture that explicitly incorporates geometric structure into its design, using a Coordinate Layer, Geometric Layer, and Evolution Layer.
result NDM provides intrinsic regularization, enhancing generalization and robustness.

Paper defines quasi-Strebel structures for meromorphic k-differentials and proves their existence.

problem Existence of quasi-Strebel structures for meromorphic k-differentials.
method Introduced quasi-Strebel structures and proved their existence for meromorphic k-differentials.
result Every differential of even order k > 2 satisfying certain conditions admits a quasi-Strebel structure.

CoLA automates efficient numerical linear algebra for complex matrix structures.

problem Efficiently solving large-scale linear algebra problems with complex matrix structures.
method Combining linear operator abstraction with compositional dispatch rules.
result Automatic and efficient numerical algorithms for various linear algebra operations.

It is known that the long line supports 212^{\aleph_1} many non-diffeomorphic differential structures. We show that the long plane supports a similar number of exotic differential structures, ie structures which are not merely diffeomorphic to the product of two structures on the factor spaces.

2012-11-20abs ↗pdf ↗

Proposes a new approach to generate sparse models from deep networks.

problem Training small networks can get stuck in local optima; over-parameterized models are preferred.
method Differential inclusion paths to generate a family of models from simple to complex.
result Algorithm converges to a critical point of empirical risks from any initializations.

Paper efficiently infers differential parameters in time-varying models using time score matching.

problem Efficiently inferring differential parameters in time-varying probabilistic models.
method Directly estimates the differential parameter using time score matching and proves consistency of the method.
result Consistent estimation of parameter derivatives in high-dimensional settings.

A new framework models uncertainty in structured temporal data using SDEs and neural networks.

problem Uncertainty quantification in machine learning applications involving structured and temporal data.
method Integrates stochastic differential equations (SDEs) with deep generative models in a variational autoencoder framework.
result Improves uncertainty quantification in machine learning applications involving structured and temporal data.

Determines algebra structure of complex differential forms operators.

problem Identifying the algebra structure of differential operators on complex-valued differential forms.
method Shows it is the universal enveloping algebra of a graded Lie algebra and determines its cohomology.
result Determines the cohomology of the graded Lie algebra with respect to various inner differentials.

The paper constructs Levi flat structures using structure sheaves and differential complexes.

problem Global solvability and regularity of Levi flat structures.
method Employing formal integrability and differential complexes, the paper constructs a resolution for the structure sheaf.
result Global exactness and Sobolev regularity of the differential complex for Levi flat structures.

MissNODAG learns cyclic causal graphs from incomplete data.

problem Causal discovery in systems with feedback loops and missing data.
method Differentiable framework integrating additive noise model and expectation-maximization.
result MissNODAG uncovers cyclic structures and missingness mechanisms from partially observed data.

Generates low-dimensional node vectors for graphs with privacy while preserving structural preferences.

problem Publishing graph node vectors can leak sensitive individual information.
method SE-PrivGEmb, a skip-gram based technique with a unified noise tolerance mechanism and negative sampling probabilities.
result Our method outperforms existing methods in structural equivalence and link prediction tasks.

This study compares different thermodynamic structure-informed neural networks for solving differential equations.

problem Improving the accuracy and physical consistency of neural network solutions to differential equations.
method Comprehensive evaluation of various thermodynamic formulations in physics-informed neural networks.
result Newtonian-residual-based PINNs fail to reliably recover physical quantities, while structure-preserving formulations enhance accuracy and robustness.

Global invariant for path structures and differential equations defined on torus.

problem Global invariant for path structures and differential equations.
method Computed as a secondary invariant from a Cartan connection on a canonical bundle.
result Formula for global invariant of second order differential equations on torus.

Efficient offline reinforcement learning with neural networks using differentiable function approximation.

problem Statistical efficiency of offline reinforcement learning with function approximators.
method Pessimistic fitted Q-learning (PFQL) and differentiable function approximation.
result Provably efficient offline reinforcement learning with differentiable function approximation.

New geometric Joyce structures on moduli spaces of quadratic differentials.

problem Constructing Joyce structures on moduli spaces of quadratic differentials.
method Isomonodromic deformations of second-order linear ODEs with rational potential.
result Construction of Joyce structures on moduli spaces of quadratic differentials.

A new layer learns abstract relations from graph structure using finite-state automata.

problem Learning abstract relations from graph structure for program analysis.
method Relaxing the problem into learning finite-state automata policies on a graph-based POMDP and training these policies using implicit differentiation.
result GFSA layer finds shortcuts in grid-world graphs and reproduces simple static analyses on Python programs.

Study non-formal pseudo-differential operators over formal ones.

problem Understanding structure of non-formal pseudo-differential operators.
method Diffeological principal bundles, smoothing connections.
result Structure of diffeological bundle of non-formal pseudo-differential operators over formal ones.

Paper analyzes multi-attribute data to estimate differences in Gaussian graphical models.

problem Estimating differences in two Gaussian graphical models with similar structure.
method Group lasso penalized D-trace loss function and ADMM algorithm for optimization.
result Consistency in support recovery and estimation in high-dimensional settings established.