New solver avoids memory issues for long differential equations.
problem Memory constraints in adaptive probabilistic ODE solvers.
method Fixed memory demands adaptive probabilistic solver using robust state estimation.
result Eliminates memory issues for long time series simulations.
C-ADAM is a new adaptive solver for complex nested problems.
problem Solving compositional problems involving nested expected values.
method Adaptive solver for non-linear functional nesting of expected values.
result C-ADAM converges to a stationary point in O(δ−2.25). Neural networks that are based on unfolding of an iterative solver, such as LISTA (learned iterative soft threshold algorithm), are widely used due to their accelerated performance. Nevertheless, as opposed to non-learned solvers, these networks are trained on a certain dictionary, and therefore they are inapplicable f…
Calibrated probabilistic solvers improve accuracy of ODE estimates.
problem Uncertainty in probabilistic ODE solutions is not well-calibrated for adaptive step sizes.
method Introduce and assess several calibration methods for probabilistic ODE solvers.
result Calibration methods interact efficiently with adaptive step-size selection, improving posteriors.
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.
DALTON improves ODE parameter estimation by learning from noisy data.
problem High sensitivity to parameters in ODEs produces unreliable parameter estimates.
method Data-adaptive probabilistic likelihood approximation for ODEs.
result DALTON produces more accurate parameter estimates than existing methods.
This paper optimizes PCE for efficient surrogate modeling in engineering.
problem Efficiently selecting polynomial regressors for surrogate modeling in computationally expensive models.
method Three state-of-the-art basis-adaptive sparse PCE methods are compared and analyzed.
result Automatic selection of the best solver and basis-adaptive scheme improves surrogate model accuracy.
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.
Neural ODEs' performance varies with numerical method, requiring adaptive step size control.
problem Neural ODEs' performance depends on the numerical method used during training.
method Proposes an adaptive step size control algorithm to ensure a valid ODE without increasing computational cost.
result Valid Neural ODEs require careful numerical method selection and step size adaptation.
INFUSER improves reasoning by co-evolving a generator and solver with adaptive curriculum.
problem Improving reasoning in language models with minimal external supervision.
method INFUSER uses a Generator and Solver to co-evolve iteratively, rewarding the Generator with an influence score and the Solver with correctness rewards.
result INFUSER outperforms self-evolution baselines by over 20% on Olympiad and SuperGPQA benchmarks.
New method solves constrained optimization problems efficiently.
problem Equality-constrained nonlinear, nonconvex optimization problems.
method Adaptive inexact Newton method with randomized iterative sketching.
result Global almost sure convergence and local linear/superlinear convergence.
Scalable solver reduces PDE uncertainty with active learning.
problem High computational cost in solving PDEs.
method Stochastic dual descent and clustering-based active learning.
result Solver scales to large number of collocation points.
Adapting deep networks to new concepts from a few examples is challenging, due to the high computational requirements of standard fine-tuning procedures. Most work on few-shot learning has thus focused on simple learning techniques for adaptation, such as nearest neighbours or gradient descent. Nonetheless, the machine…
During the development of autonomous systems such as driverless cars, it is important to characterize the scenarios that are most likely to result in failure. Adaptive Stress Testing (AST) provides a way to search for the most-likely failure scenario as a Markov decision process (MDP). Our previous work used a deep rei…
In this study, we focus on the market clearing problem of Turkish day-ahead electricity market. We propose a mathematical model by extending the variety of bid types for different price regions. The commercial solvers may not find any feasible solution for the proposed problem in some instances within the given time li…
ACA method improves gradient estimation for neural ODEs, reducing error and training time.
problem Inaccurate gradient estimation methods hinder the performance of neural ODEs on benchmark tasks.
method Adaptive Checkpoint Adjoint (ACA) method that applies trajectory checkpointing, deletes redundant components, and supports adaptive solvers.
result ACA reduces error rate by half and training time by half compared to adjoint and naive methods on image classification tasks.
Continuous-time optimal stopping solved with deep reinforcement learning
problem Optimal stopping problems in continuous time
method CARLOS (Continuous-time Adaptive Reinforcement Learning for Optimal Stopping)
result Higher prices than existing Bermudan solvers, approaching American upper bound
CADO optimizes heatmap-based solvers for cost minimization, overcoming performance limitations.
problem Heatmap-based solvers lack objective alignment for cost minimization.
method CADO uses Reinforcement Learning to optimize solution cost directly, introducing Label-Centered Reward and Hybrid Fine-Tuning.
result CADO achieves state-of-the-art performance across diverse benchmarks.
Modeling bone microarchitecture adaptation using geometric flows.
problem Bone microarchitecture adaptation modeling.
method Advection and mean curvature flow model with a sphere as a test case.
result Closed-form solution for sphere under advection and mean curvature flow.
A new DRL scheme optimizes solving large graphs' maximum independent set problem.
problem Efficiently solving maximum independent set problems on large graphs.
method Learning what to defer (LwD) to adaptively control the number of stages.
result Significantly outperforms state-of-the-art DRL and conventional solvers.
Screening rules allow to early discard irrelevant variables from the optimization in Lasso problems, or its derivatives, making solvers faster. In this paper, we propose new versions of the so-called safe rules for the Lasso. Based on duality gap considerations, our new rules create safe test regions whose d…
Meta-learning improves anomaly detection with few labeled instances.
problem High requirement of training data for neural network-based anomaly detection.
method Meta-learning framework with one-class classification and generalized eigenvalue problem.
result Meta-learning method achieves better performance than existing methods on various datasets.
Integer programming (IP) is a general optimization framework widely applicable to a variety of unstructured and structured problems arising in, e.g., scheduling, production planning, and graph optimization. As IP models many provably hard to solve problems, modern IP solvers rely on many heuristics. These heuristics ar…
Understanding the global optimality in deep learning (DL) has been attracting more and more attention recently. Conventional DL solvers, however, have not been developed intentionally to seek for such global optimality. In this paper we propose a novel approximation algorithm, BPGrad, towards optimizing deep models glo…
We show how the discovery of robust scalable numerical solvers for arbitrary bounded linear operators can be automated as a Game Theory problem by reformulating the process of computing with partial information and limited resources as that of playing underlying hierarchies of adversarial information games. When the so…
A new ML method speeds up PDE simulations without needing classical training.
problem Accelerating transient PDE simulations using machine learning.
method Online-learned preconditioners using a bandit algorithm.
result One-shot acceleration of PDE simulations.
LR-EDNN reduces PDE solver complexity by limiting network weights to low-rank subspace.
problem Efficiently solving time-dependent PDEs with deep neural networks.
method Low-rank constraint on network weights using SVD for efficient parameter updates.
result LR-EDNN achieves comparable accuracy to full EDNN with fewer parameters and lower cost.
Paper develops MMOT framework for financial applications with neural acceleration.
problem Financial optimization and calibration under multi-period martingale constraints.
method Theoretical analysis, incremental updates, adaptive sparse grids, hybrid neural-projection solver.
result Neural solver achieves 1597x speedup for real-time applications.
INFUSER improves reasoning by self-evolving with a generator and solver that co-learn from unstructured documents.
problem Improving reasoning through self-evolution
method INFUSER uses a generator and solver co-evolving in a document pool to improve reasoning.
result INFUSER outperforms strong self-evolution baselines on Olympiad and SuperGPQA benchmarks.
Improved neural-ODE for faster convergence and stability.
problem Stability, consistency, and convergence issues in neural-ODE solvers.
method Proposed a first-order Nesterov's accelerated gradient (NAG) based ODE-solver.
result Efficacy demonstrated in three tasks: supervised classification, density estimation, and time-series modelling.
Machine learning predicts flight connections for airline crew scheduling.
problem Predicting the next connecting flight for airline crews.
method Adapted neural network for multiclass classification from historical data.
result High accuracy (99.7%) in flight connection prediction.
We introduce a new family of deep neural network models. Instead of specifying a discrete sequence of hidden layers, we parameterize the derivative of the hidden state using a neural network. The output of the network is computed using a black-box differential equation solver. These continuous-depth models have constan…
G-FuNK learns solutions for nonlinear PDEs on multiple domains and parameters.
problem Predicting time-dependent dynamics of complex systems governed by nonlinear PDEs with varying parameters and domains.
method Graph Fourier Neural Kernels combining domain-adapted and transferable components for non-diffusive and diffusive terms.
result G-FuNK achieves low relative errors on unseen domains and fiber fields, significantly accelerating predictions.
Efficient solver for nonconvex tensor regularization reduces computational cost.
problem Computational inefficiency in extending nonconvex regularization to tensor learning.
method Proximal average algorithm with adaptive momentum, maintaining sparse plus low-rank structure.
result Shows good statistical performance and accuracy on tensor completion problems.
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.
AdaDPS uses side information to improve private adaptive optimization.
problem Private adaptive optimization methods degrade when training with differential privacy.
method AdaDPS uses non-sensitive side information to precondition gradients.
result AdaDPS reduces the amount of noise needed for similar privacy guarantees, improving optimization performance.
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.
New algorithm reduces sketching dimension to effective problem size.
problem Solving L2-regularized least-squares problems efficiently.
method Randomized algorithm using Gaussian and SRHT embeddings.
result Preserves convergence guarantees with reduced embedding dimension.
FlowKac solves high-dimensional Fokker-Planck equations efficiently.
problem Intractability of Fokker-Planck equation solutions in high dimensions.
method Reformulates Fokker-Planck using Feynman-Kac, adaptive stochastic sampling, and normalizing flows.
result Significant computational efficiency and accuracy improvements over existing methods.
We propose a new architecture called Memory-Augmented Encoder-Solver (MAES) that enables transfer learning to solve complex working memory tasks adapted from cognitive psychology. It uses dual recurrent neural network controllers, inside the encoder and solver, respectively, that interface with a shared memory module a…
Flexible algorithms for maximizing rewards in structured bandits.
problem Reward maximization in structured stochastic multi-armed bandit problems.
method Asymptotically optimal algorithms using iterative saddle-point solvers.
result Achieves optimal performance with minimal computational burden.
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.
We propose a unified and systematic framework for performing online nonnegative matrix factorization in the presence of outliers. Our framework is particularly suited to large-scale data. We propose two solvers based on projected gradient descent and the alternating direction method of multipliers. We prove that the se…
In applications of Gaussian processes where quantification of uncertainty is of primary interest, it is necessary to accurately characterize the posterior distribution over covariance parameters. This paper proposes an adaptation of the Stochastic Gradient Langevin Dynamics algorithm to draw samples from the posterior …
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.
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 method approximates POMDPs with PB-MDPs, providing error bounds and practical algorithms.
problem Difficulty in solving POMDPs with continuous or hybrid state and observation spaces.
method Bounding particle filtering error and adapting MDP algorithms to POMDPs.
result General theory and practical algorithms for POMDPs with no direct dependence on state and observation space sizes.
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.