arXiv research

Study analyzes 3,171 stocks to pick efficient portfolios using quantum and classical solvers.

Although optimization is the longstanding algorithmic backbone of machine learning, new models still require the time-consuming implementation of new solvers. As a result, there are thousands of implementations of optimization algorithms for machine learning problems. A natural question is, if it is always necessary to…

A new method combines classical and machine learning PDE solvers efficiently.

Quantum machine learning solves high-dimensional PDEs with lower variance and improved accuracy.

This work introduces a new loss function to improve the efficiency of optimization-based PDE solvers.

A new ML method speeds up PDE simulations without needing classical training.

AI methods often fail to outperform classical CPU-based solvers on Maximum Independent Set problems.

We study two fundamental questions in neuro-symbolic computing: can deep learning tackle challenging problems in logics end-to-end, and can neural networks learn the semantics of logics. In this work we focus on linear-time temporal logic (LTL), as it is widely used in verification. We train a Transformer on the proble…

Extends GENO framework for GPU optimization of constrained ML problems.

There is resurging interest, in statistics and machine learning, in solvers for ordinary differential equations (ODEs) that return probability measures instead of point estimates. Recently, Conrad et al. introduced a sampling-based class of methods that are 'well-calibrated' in a specific sense. But the computational c…

Deep learning matches classical feature-based AS models for TSP.

Parallel-in-time solver reduces ODE simulation time from linear to logarithmic.

Leveraging on the convexity of the Lasso problem , screening rules help in accelerating solvers by discarding irrelevant variables, during the optimization process. However, because they provide better theoretical guarantees in identifying relevant variables, several non-convex regularizers for the Lasso have been prop…

Calibrated probabilistic solvers improve accuracy of ODE estimates.

New framework for probabilistic linear solvers reduces manual effort.

New method stabilizes probabilistic ODE solvers for high accuracy.

New method solves PDEs for any initial condition without retraining.

Runge-Kutta methods are the classic family of solvers for ordinary differential equations (ODEs), and the basis for the state of the art. Like most numerical methods, they return point estimates. We construct a family of probabilistic numerical methods that instead return a Gauss-Markov process defining a probability d…

Likelihood-free (a.k.a. simulation-based) inference problems are inverse problems with expensive, or intractable, forward models. ODE inverse problems are commonly treated as likelihood-free, as their forward map has to be numerically approximated by an ODE solver. This, however, is not a fundamental constraint but jus…

New method uses Gaussian processes to improve PDE solver accuracy.

DC3 uses deep learning to solve hard-constrained optimization problems efficiently.

Probabilistic solvers improve stability for stiff systems.

Paper develops MMOT framework for financial applications with neural acceleration.

Holistic GLMs add constraints for better model quality.

Prob-GParareal adds uncertainty quantification to PinT solvers for differential equations.

Quantum algorithm speeds up MIP solving by a near-quadratic factor.

Graph neural networks improve AMG convergence for sparse systems.

Continuous-time optimal stopping solved with deep reinforcement learning

Like many numerical methods, solvers for initial value problems (IVPs) on ordinary differential equations estimate an analytically intractable quantity, using the results of tractable computations as inputs. This structure is closely connected to the notion of inference on latent variables in statistics. We describe a …

Exact solver speeds up Weston-Watkins SVM subproblem significantly.

Optimizes neural networks with blackbox solvers using Time-cost Regularization.

End-to-end portfolio optimization using quantum annealing for financial decision problems.

Recommender systems play an essential role in the modern business world. They recommend favorable items like books, movies, and search queries to users based on their past preferences. Applying similar ideas and techniques to Monte Carlo simulations of physical systems boosts their efficiency without sacrificing accura…

The paper speeds up hyperparameter optimisation in Gaussian processes.

New solver MPLP++ outperforms existing solvers for dense graph models.

CRA improves UL-based CO solvers by dynamically smoothing and enforcing discreteness.

CNN outperforms other methods in gravity inversion.

We analyze the computational complexity of Quantum Sparse Support Vector Machine, a linear classifier that minimizes the hinge loss and the $L_1$ norm of the feature weights vector and relies on a quantum linear programming solver instead of a classical solver. Sparse SVM leads to sparse models that use only a small fr…

Study compares 5 ODE solvers on 3 case studies, finding varying accuracy.

Higher-order ODE solvers improve deep learning performance.

SA-Solver improves stochastic sampling from DPMs.

Accelerates data generation in score-based models.

New taxonomy and improved solvers for discrete energy minimization.

End-to-end trainable graph matching using improved combinatorial solvers.

A mesh-free method solves continuum-marginal optimal transport problems.

We present a quantum interior-point method (IPM) for second-order cone programming (SOCP) that runs in time $\widetilde{O} \left( n\sqrt{r} \frac{ζκ}{δ^2} \log \left(1/ε\right) \right)$ where $r$ is the rank and $n$ the dimension of the SOCP, $δ$ bounds the distance of intermediate solutions from the cone boundary, $ζ$…

MIP-GNN uses graph neural networks to predict variable biases for MIP solvers.

Developing stable and scalable probabilistic ODE solvers for stiff and high-dimensional problems.