New solver MPLP++ outperforms existing solvers for dense graph models.
problem Efficiently solving dense, discrete Graphical Models with pairwise potentials.
method Dual Block-Coordinate Ascent with MPLP++ modification.
result MPLP++ significantly outperforms existing solvers, including TRWS.
New EOT solvers estimate both plans and maps efficiently.
problem Difficulty in tuning entropic regularization strength in EOT solvers.
method Time discretization and proper parameter scheduling to optimize EOT computation.
result ProgOT is faster and more robust, outperforming neural networks.
New taxonomy and improved solvers for discrete energy minimization.
problem Maximum-a-posteriori inference in discrete graphical models.
method Dual block-coordinate ascent rule, theoretical analysis, new solver variants.
result Improved state-of-the-art solver outperforming existing methods on all test instances.
GENOT matches cells across data modalities using neural OT solvers.
problem Scalability, privacy, and out-of-sample estimation issues in traditional OT solvers.
method Learn stochastic maps, parameterize OT maps, relax mass conservation, integrate quadratic solvers.
result Demonstrates significant potential for enhancing therapeutic strategies.
Efficiently solves MRF inference problems with semidefinite programming.
problem Computing partition function or MAP estimate in binary and multi-class MRFs.
method Coordinate-descent-based fast semidefinite solver for SDPs.
result Substantially outperforms existing state-of-the-art methods in approximate inference.
ThiopheneIV is a new solver for implied volatility with proven monotonicity.
problem Efficiently solving implied volatility in financial models.
method Monotone core with Euler-Chebyshev and Halley steps, exact arithmetic proof, practical boundary handling.
result ThiopheneIV agrees closely with multiprecision Black reference prices at low latency.
Differentiable layers for convex optimization problems.
problem Rigidity of existing differentiable optimization layers.
method Disciplined parametrized programming and affine-solver-affine form.
result Efficient analytical differentiation through convex programs.
DiffOPF solves multi-valued OPF problems by sampling from system history.
problem Multi-valued and non-convex OPF problems due to system parameter variability.
method DiffOPF treats OPF as a conditional sampling problem, learning from historical data.
result DiffOPF enables statistically credible warm starts with favorable cost and constraint satisfaction trade-offs.
SATNet integrates logical reasoning into deep learning with a differentiable MAXSAT solver.
problem Integrating logical reasoning into deep learning architectures.
method Differentiable MAXSAT solver based on fast coordinate descent for SDP.
result Minimally supervised learning of logical structures in deep learning systems.
The goal of the present paper is to propose an enhanced ordinary differential equations solver by exploitation of the powerful equivalence method of Élie Cartan. This solver returns a target equation equivalent to the equation to be solved and the transformation realizing the equivalence. The target ODE is a member of …
Neural solver computes Wasserstein geodesics and velocity fields efficiently.
problem Computing Wasserstein geodesics and velocity fields efficiently.
method Sample-based neural network approach to solve the minimax problem.
result Directly samples from target distribution and estimates velocity field.
Method uses neural networks to solve combinatorial problems.
problem Solving combinatorial problems on raw input data.
method Integrates blackbox combinatorial solvers into neural networks.
result Efficient backward pass through blackbox solvers implemented.
New algorithm optimizes variational objective for marginal inference.
problem Optimizing the tree-reweighted variational objective over the marginal polytope.
method Barrier Frank-Wolfe algorithm based on conditional gradient method, leveraging MAP solvers.
result More accurate results than TRW algorithms that optimize over local consistency relaxation.
LP relaxations often provide tight solutions in structured prediction tasks.
problem Finding tight solutions for complex scoring functions in structured prediction.
method Theoretical explanation of why LP relaxations are often tight on real-world instances.
result Learning with LP relaxed inference encourages integrality of training instances, and tightness generalizes from train to test data.
The paper tackles efficient computation of optimal transport by approximating conjugates with amortized optimization.
problem Efficient computation of convex conjugates in optimal transport is challenging and limits the quality of transport maps.
method The approach combines amortized approximations of conjugates with a fine-tuning solver to improve transport map quality.
result The method significantly improves the quality of transport maps for the Wasserstein-2 benchmark and models many 2D couplings and flows.
A scalable method for training prediction models in predict-then-optimize
problem Training prediction models in the predict-then-optimize paradigm
method Decision-focused learning pipeline
result Decision quality competitive with state-of-the-art methods while reducing training time
New method uses Gaussian ODE filtering to approximate likelihoods for fast ODE inverse problems.
problem Intractable forward models in likelihood-free inference, especially for ODEs.
method Gaussian ODE filtering to construct local Gaussian likelihood approximations.
result New solvers outperform standard likelihood-free approaches on benchmark systems.
In this paper we relate the partition function to the max-statistics of random variables. In particular, we provide a novel framework for approximating and bounding the partition function using MAP inference on randomly perturbed models. As a result, we can use efficient MAP solvers such as graph-cuts to evaluate the c…
Graph neural networks improve AMG convergence for sparse systems.
problem Efficiently constructing algebraic multigrid prolongation operators for sparse linear systems.
method Train a graph neural network to learn prolongation operators from matrix classes, using an unsupervised loss function.
result Improved convergence rates compared to classical AMG methods.
Exact solver speeds up Weston-Watkins SVM subproblem significantly.
problem Improving performance of Weston-Watkins multiclass SVM.
method Novel reparametrization for exact subproblem solving.
result Significant speed-up over state-of-the-art solvers for large number of classes.
Recommender systems improve quantum Monte Carlo simulations.
problem Efficiency of quantum Monte Carlo methods without sacrificing accuracy.
method Quantum to classical mapping and molecular simulation techniques.
result Classical molecular gas model reproduces quantum distributions efficiently.
Optimizes neural networks with blackbox solvers using Time-cost Regularization.
problem Improving neural network performance by integrating efficient solvers for complex problems.
method Optimizes both the primary loss function and the performance of the blackbox solver using Time-cost Regularization. Introduces a hyper-blackbox concept to learn blackbox parameters.
result Significant improvement in neural network performance through optimization of blackbox solvers.
Much effort has been directed at algorithms for obtaining the highest probability configuration in a probabilistic random field model known as the maximum a posteriori (MAP) inference problem. In many situations, one could benefit from having not just a single solution, but the top M most probable solutions known as th…
Study analyzes 3,171 stocks to pick efficient portfolios using quantum and classical solvers.
problem Creating efficient stock portfolios from a large dataset.
method Used classical and quantum solvers to optimize portfolios of 3,171 US stocks.
result Demonstrated the effectiveness of quantum and classical solvers in portfolio optimization.
The paper speeds up hyperparameter optimisation in Gaussian processes.
problem Scaling hyperparameter optimisation to large datasets.
method Improvements to linear system solvers (pathwise gradient, warm starting, early stopping).
result Speed-ups of up to 72x and residual norm decreases of up to 7x.
MAP inference for general energy functions remains a challenging problem. While most efforts are channeled towards improving the linear programming (LP) based relaxation, this work is motivated by the quadratic programming (QP) relaxation. We propose a novel MAP relaxation that penalizes the Kullback-Leibler divergence…
GENO framework generates efficient solvers for machine learning problems.
problem Designing efficient solvers for machine learning problems.
method GENO framework combines a modeling language with a generic solver to generate solvers from optimization problem specifications.
result Automatically generated solvers are as efficient as well-engineered specialized solvers and orders of magnitude more efficient than classical modeling language plus solver approaches.
Neural network learns fast PDE solvers with proven guarantees.
problem Designing fast iterative solvers for specific PDE problems.
method Learn to modify an existing solver using a deep neural network.
result Achieves 2-3 times speedup compared to state-of-the-art solvers.
CRA improves UL-based CO solvers by dynamically smoothing and enforcing discreteness.
problem Local optima and artificial rounding issues in UL-based CO solvers.
method Continuous Relaxation Annealing (CRA) strategy that dynamically shifts from continuous to discrete solutions.
result Significantly enhances UL-based CO solver performance and eliminates artificial rounding.
LFlows model fluid densities and velocities using invertible maps that satisfy the continuity equation.
problem Modeling fluid densities and velocities continuously in space and time.
method LFlows are based on invertible maps that satisfy the continuity equation, derived from classical theory of Lagrangian flows for smooth vector fields.
result LFlows show higher predictive accuracy in density modeling tasks compared to competing models in 2D and 3D.
Study compares 5 ODE solvers on 3 case studies, finding varying accuracy.
problem Comparing estimation accuracy of 5 ODE solvers on 3 case studies.
method Used 5 different numerical ODE solvers (Euler's, Heun's, Midpoint, Runge-Kutta 4th order, ODE45) on 3 case studies and compared their results.
result Different solvers have varying accuracy depending on the case study.
Direct neural network calibration outperforms indirect method for rough volatility models.
problem Calibrating volatility models with neural networks.
method Comparison of direct and indirect neural network approaches for volatility model calibration.
result Direct approach outperforms indirect approach for rough volatility models.
A new method combines classical and machine learning PDE solvers efficiently.
problem Combining classical and machine learning PDE solvers to reduce computational cost and improve accuracy.
method Proposes an approximate greedy router to select solvers at each iteration, mimicking a greedy approach.
result Consistently reduces final error and AUC of the error trajectory compared to single-solver baselines and hybrid approaches.
Higher-order ODE solvers improve deep learning performance.
problem Improving deep learning performance using higher-order ODE solvers.
method Evaluation and improvement of Runge-Kutta (RK) methods for deep learning.
result Higher-order RK solvers can improve deep learning performance by incorporating key ingredients of optimizers.
SA-Solver improves stochastic sampling from DPMs.
problem Efficient sampling from Diffusion Probabilistic Models (DPMs) is time-consuming.
method Proposes SA-Solver, an improved stochastic Adams method for solving diffusion SDE.
result SA-Solver achieves improved or comparable performance compared to SOTA methods for few-step sampling.
FASTA improves brain imaging by solving TV-regularized problems faster.
problem Solving ill-conditioned total variation problems in brain imaging.
method fAASTA, a variant of FISTA, refines the TV proximal operator to balance gradient and proximal steps.
result fAASTA significantly reduces the number of gradient steps in brain imaging problems.
Accelerates data generation in score-based models.
problem Slow generation of realistic data by score-based models.
method Developed an adaptive step size SDE solver.
result Generates data 2-10 times faster with high quality.
New deep learning solver for high-dimensional derivative pricing.
problem High-dimensional derivatives pricing problems.
method Combines deep learning with least square regression for backward SDE solving.
result Accurate and efficient pricing of complex derivatives.
CNN outperforms other methods in gravity inversion.
problem Estimating subsurface density from gravitational field data.
method CNN, VAEs, GANs, iterative solvers (GD, GMRES, LGMRES, ICG).
result CNN provides the most reliable reconstructions.
End-to-end trainable graph matching using improved combinatorial solvers.
problem Graph matching in deep learning.
method Combining deep learning with optimized combinatorial solvers.
result Advances state-of-the-art on deep graph matching benchmarks.
MIP-GNN uses graph neural networks to predict variable biases for MIP solvers.
problem Improving combinatorial optimization through data-driven insights.
method Encoding MILP interactions as graphs, training a graph neural network to predict variable biases, and guiding the MIP solver with these predictions.
result Significant improvements in solving binary MILPs compared to default settings of state-of-the-art solvers.
DPM-Solver speeds up DPM sampling to 10-20 function evaluations.
problem Slow sampling from Diffusion Probabilistic Models (DPMs).
method Exact formulation of diffusion ODE solutions, using change-of-variable and exponentially weighted integral.
result Generates high-quality samples in 10-20 function evaluations.
Developing stable and scalable probabilistic ODE solvers for stiff and high-dimensional problems.
problem Stiff and high-dimensional ODEs
method Matrix-free update step and iterative re-linearization
result Improved stability and scalability
The paper improves ODE solvers by integrating diverse information types.
problem Improving accuracy and physical meaningfulness of ODE solutions.
method Leveraging probabilistic solvers to include second-order information and physical conservation laws.
result Solutions become more accurate and physically meaningful with additional information.
Parallel-in-time solver reduces ODE simulation time from linear to logarithmic.
problem Efficiently solving ordinary differential equations (ODEs) with reduced computational cost.
method Formulated a parallel-in-time probabilistic numerical ODE solver using time-parallel formulation of iterated extended Kalman smoothers.
result Reduces span cost from linear to logarithmic in the number of time steps.
Ada-LISTA adapts neural solvers for varying models.
problem Adapting neural solvers for varying models.
method Ada-LISTA receives pairs of signals and dictionaries, learns a universal architecture, and solves sparse coding in linear rate.
result Ada-LISTA solves sparse coding in linear rate for varying models.
The paper tackles MAP inference over non-convex constraints in safety-critical settings.
problem Efficiently computing MAP predictions subject to non-convex constraints is challenging.
method The paper investigates conditions for exact and efficient MAP inference over continuous variables and devises scalable algorithms for both tractable and general cases.
result The proposed methods outperform constraint-agnostic baselines and scale to complex densities.
ML4CO uses machine learning to improve combinatorial optimization solvers.
problem Solving combinatorial problems in practice often involves related data distributions.
method Replacing heuristic components with machine learning approaches.
result Improved state-of-the-art combinatorial optimization solvers.