Improved Anderson acceleration speeds up nonlinear optimization.
problem Optimizing nonlinear functions efficiently.
method Combining Anderson acceleration with Chebyshev polynomials.
result Achieves optimal convergence rate for nonlinear problems.
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.
169,181 papers · 148 categories
Trend · papers per month
48 results for “nonlinear acceleration”
Paper accelerates nonlinear mapping in online systems with lower time complexity.
problem Speeding up nonlinear mapping in online systems.
method Integrates an acceleration module into Dendrite Net (DD) to reduce time complexity.
result DD with AC has lower time complexity while maintaining nonlinear mapping and system identification properties.
RNA accelerates CNNs for image recognition.
problem Improving the optimization process of CNNs for image recognition.
method Regularized Nonlinear Acceleration (RNA) applied to neural networks.
result RNA improves the optimization process of CNNs slightly.
New RNA scheme accelerates gradient methods online and improves convergence.
problem Improving convergence rates of gradient methods.
method Adapting Regularized Nonlinear Acceleration (RNA) to handle faster multistep algorithms.
result Optimal complexity bounds and asymptotically optimal rates for convex minimization problems.
New algorithms accelerate solving nonlinear matrix decomposition with ReLU.
problem Nonlinear matrix decomposition with ReLU function.
method Two new algorithms: A-NMD and 3B-NMD, with adaptive extrapolation and block parametrization.
result Effective algorithms accelerate solving ReLU-NMD problems.
Parallelizes feedforward computation using nonlinear equation solving.
problem Sequential nature of feedforward computation limits parallelization.
method Frame feedforward computation as solving nonlinear equations; use Jacobi or Gauss-Seidel methods for parallel updates.
result Accelerates feedforward computation with reduced parallelizable iterations.
Accelerates coordinate descent methods for machine learning problems.
problem Slowness of coordinate descent methods in machine learning.
method Extrapolation-based accelerated coordinate descent.
result Significant speed-up in practice compared to existing methods.
New algorithms optimize constrained problems faster, avoiding full set optimization.
problem Optimizing constrained problems efficiently and quickly.
method Designing accelerated first-order algorithms that avoid full set optimization.
result Proved convergence to stationary points in nonconvex settings and accelerated rates in convex settings.
Proposes a new AFT model for nonlinear survival data.
problem Limited ability of classical AFT models to represent nonlinear relationships and handle complex covariate structures.
method Structured nonparametric extension using Kolmogorov--Arnold representations and unified censoring-adjusted losses.
result Method captures nonlinear effects and recovers linear structure when appropriate.
Paper discovers structural dynamics equations from only acceleration data.
problem Discovering equations from only acceleration measurements in structural dynamics.
method Library-based approach with Approximate Bayesian Computation (ABC) prioritizing parsimonious models.
result Efficacy demonstrated in four structural dynamics examples, including linear and nonlinear systems.
Autoencoders discover and accelerate molecular dynamics simulations.
problem Efficient sampling of macromolecular folding landscapes with high free energy barriers.
method Employing auto-associative artificial neural networks to learn nonlinear collective variables (CVs) that are explicit and differentiable functions of atomic coordinates.
result Substantial speedups in exploration of configurational space and discovery of data-driven CVs.
DynNet models dynamic responses of linear and nonlinear systems with fewer variables and higher accuracy.
problem Predicting dynamic responses of linear and nonlinear systems.
method Physics-based recurrent neural network with optimized architecture and training techniques.
result Higher accuracy and fewer trainable variables compared to existing models.
Deep neural networks improve AFT model for non-linear predictors.
problem Nonlinearity in predictors of AFT models.
method Apply DNNs to fit AFT models using Gehan-type loss and sub-sampling.
result DeepR-AFT outperforms parametric and semiparametric models.
Improved Convergence Factor of Windowed Anderson Acceleration for Symmetric Fixed-Point Iterationsmath.NA
Improved convergence of fixed-point methods using windowed Anderson acceleration.
problem Improving convergence of fixed-point methods for symmetric operators.
method Windowed Anderson acceleration for symmetric fixed-point iterations.
result Windowed Anderson acceleration improves convergence over standard fixed-point methods.
The paper connects dynamical systems to ADMM for solving nonsmooth constrained problems.
problem Solving nonsmooth and constrained optimization problems.
method Developed differential inclusions for accelerated ADMM variants and analyzed their convergence rates.
result Derived rates of convergence for the dynamical systems under different settings, showing tradeoffs between damping strategies.
New Zap Q-learning accelerates reinforcement learning with neural networks.
problem Accelerate convergence of reinforcement learning algorithms.
method Introduces a new framework for analysis of stochastic approximation algorithms, proving consistency under non-degeneracy assumption.
result Zap Q-learning with neural network function approximation converges quickly and is robust to function approximation architecture choice.
Survey on extragradient methods for solving nonlinear equations and inclusions.
problem Approximating solutions of nonlinear equations and inclusions.
method Unified convergence analysis of extragradient and its variants.
result Sublinear convergence rates for different classes of algorithms.
We calculate in the strong coupling and large N limit the energy emitted by an accelerated external charge in SU(N) Yang-Mills theory, using the AdS/CFT correspondence. We find that the energy is a local functional of the trajectory of the charge. It coincides up to an overall factor with the Lienard formu…
Ubiquitous power law scaling in nonlinear self-excited Hawkes processescond-mat.stat-mech
New mechanism found for power laws including Zipf's law.
problem Understanding the ubiquity of power law distributions.
method Introduced nonlinear self-excited Hawkes processes with fast-accelerating intensities.
result Wide class of nonlinear Hawkes processes have power law intensity PDFs.
Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depthcs.LG
New insights into GNN optimization reveal skip connections and depth accelerate training.
problem Understanding and optimizing the training of Graph Neural Networks (GNNs).
method Analysis of gradient dynamics in linearized GNNs and empirical validation.
result GNNs are implicitly accelerated by skip connections, more depth, and good label distribution during training.
New accelerators for EM improve convergence speed in complex mixture models.
problem Improving the convergence speed of the EM algorithm for complex mixture models.
method Derive a new operator connecting global descent and local convergence, and use it to develop two acceleration strategies.
result Two new acceleration strategies (G-Accelerator and Geo-Adaptive) significantly improve EM algorithm performance.
GPU-accelerates multiuser detection for 5G URLLC systems.
problem Efficiently detecting payloads in OFDM frames with ultra-low latency.
method Implemented partially linear multiuser detection in RKHSs on a GPU-accelerated platform.
result Sub-millisecond latency detection in 5G URLLC systems.
Proposes momentum methods for Lie groups, improving on classical algorithms.
problem Optimization on nonlinear spaces, especially Lie groups.
method Generalizes Nesterov's Accelerated Gradient method to Lie groups.
result Demonstrates faster convergence for NAG-like methods on Lie groups.
Keeping a basic tenet of economic theory, rational expectations, we model the nonlinear positive feedback between agents in the stock market as an interplay between nonlinearity and multiplicative noise. The derived hyperbolic stochastic finite-time singularity formula transforms a Gaussian white noise into a rich time…
Chebyshev steps improve convergence in deep-unfolded gradient descent.
problem Improving convergence speed in iterative algorithms.
method Introducing Chebyshev steps to bound convergence rate of gradient descent.
result Chebyshev steps lead to asymptotically optimal convergence rate.
Large stepsize GD for logistic regression converges faster than expected.
problem Optimizing logistic regression with large step sizes.
method Gradient descent with large stepsize applied to logistic regression.
result GD converges to a lower loss in fewer steps than expected.
CodeX improves DNN acceleration on FPGAs by encoding and customizing bitwidth.
problem Efficiently accelerating deep neural networks on FPGAs with limited memory.
method Nonlinear encoding, automated bitwidth customization, FPGA streaming buffers.
result Average 4.65x throughput improvement on MNIST, SVHN, CIFAR-10.
Dropout improves neural networks by accelerating gradient flow.
problem Understanding why dropout works and improving neural network performance.
method Proposed an optimization technique to push input towards saturation area of activation functions.
result Gradient acceleration in activation function (GAAF) improves image classification performance.
Neural operators correct PDE residuals to improve BIP solutions.
problem Reducing error in infinite-dimensional Bayesian inverse problems with neural operators.
method Error correction using PDE residuals to improve neural operator approximation.
result Trained neural operators with error correction achieve a quadratic reduction in approximation error.
In this paper, we present a generic framework to extend existing uniformly optimal convex programming algorithms to solve more general nonlinear, possibly nonconvex, optimization problems. The basic idea is to incorporate a local search step (gradient descent or Quasi-Newton iteration) into these uniformly optimal conv…
Paper introduces XBART for nonlinear regression, outperforming XGBoost.
problem Nonlinear regression problems, especially in speed and accuracy.
method Combines Bayesian modeling and recursive partitioning for efficient, accurate predictions.
result XBART provides faster and more accurate predictions than XGBoost.
Unified view of accelerated and stochastic optimization methods.
problem Optimization challenges in machine learning and physics.
method Unified gradient flow approach to proximal algorithms and their accelerated variants.
result Unified framework for accelerated and stochastic optimization methods.
The geometry of systems of third order differential equations induced by second order Lagrangiansmath.DG
A dynamical system on the total space of the fibre bundle of second order accelerations, , is defined as a third order vector field on , called semispray, which is mapped by the second order tangent structure into one of the Liouville vector field. For a regular Lagrangian of second order we prove that …
DeepONet accelerates reliability analysis of stochastic nonlinear systems.
problem Time-dependent reliability analysis of systems with stochastic forcing.
method DeepONet, a novel operator network, learns function-to-function mappings.
result DeepONet efficiently and accurately predicts system responses.
Exact asymptotic solutions to nonlinear Hawkes processes: a systematic classification of the steady-state solutionscond-mat.stat-mech
Exact asymptotic solutions found for nonlinear Hawkes processes.
problem Analytical solutions for nonlinear Hawkes processes with positive and negative feedbacks.
method Field master equation approach to classify steady-state solutions.
result Explicit power law formulas for steady-state intensity distributions , with as a function of parameters.
Study uses machine learning to recommend best solvers for slab transport problems.
problem Auto-selecting the best solvers for transport problems in uniform slabs.
method Three solvers (Richardson, diffusion synthetic acceleration, nonlinear diffusion acceleration) and five machine learning algorithms (linear discriminant analysis, K-nearest neighbors, support vector machine, random forest, neural networks) were tested.
result Random forest and K-nearest neighbors showed potential as best solvers for classification problems.
GNet uses Gaussian processes for scalable, flexible neural networks.
problem Large-scale predictive modeling with high computational and storage costs.
method GNet employs Gaussian processes with nonparametric activation functions and a fast algorithm for training and predictions.
result GNet achieves competitive performance across various test problems, including nonlinear function prediction and real-world data regression.
GNet uses Gaussian processes for scalable, flexible neural networks.
problem Large-scale predictive modeling with high computational and storage costs.
method GNet employs Gaussian processes with nonparametric activation functions and a fast algorithm for efficient training and predictions.
result GNet achieves competitive performance across various test problems, including nonlinear function prediction and real-world data regression.
NDI enables high-quality QSM without parameter tuning.
problem Quantitative Susceptibility Mapping (QSM) with regularization tuning issues.
method Nonlinear Dipole Inversion (NDI) using a physics-based forward model and a Variational Network (VN).
result NDI achieves high-quality QSM from as few as 2-direction data.
This work uses a scalable approach to identify partially observed nonlinear systems.
problem Offline identification of partially observed nonlinear systems.
method Certainty-equivalent expectation-maximization (CEEM) as block coordinate-ascent.
result The CEEM approach can identify high-dimensional systems reliably and efficiently.
New algorithm speeds up diffusion model sampling 4-14 times.
problem Time-consuming sampling from diffusion models.
method Parallelizing autoregressive process through fixed-point iteration.
result ParaTAA reduces inference steps by 4-14 times.
Optimization on manifolds: A symplectic approachcond-mat.stat-mech
New method solves optimization problems on manifolds using symplectic integrators.
problem Optimization tasks on manifolds with nonlinear constraints.
method Dissipative extension of Dirac's theory of constrained Hamiltonian systems and geometric/symplectic numerical integrators.
result Developed algorithms achieve optimal convergence rates locally.
New adaptive algorithms improve learning rate and reduce complexity.
problem Nonlinear system identification and prediction with large parameters.
method Data-selective adaptive kernel normalized least-mean square (KNLMS) algorithms.
result Proposed algorithms outperform existing methods in nonlinear system identification and prediction.
Develops new algorithms for solving root-finding problems in large-scale settings.
problem Solving nonlinear equations in large-scale settings.
method Randomized block-coordinate optimistic gradient algorithms.
result Achieves convergence rates of and for root-finding problems.
GrokAlign aligns Jacobians to accelerate grokking in deep networks.
problem Accelerating the training dynamics of deep networks to avoid delayed generalisation and robustness.
method Aligning the Jacobians of a deep network with the training data to ensure grokking under a low-rank assumption.
result GrokAlign regularizes Jacobians to induce grokking sooner than conventional methods.
Accelerating PDE-constrained Inverse Solutions with Deep Learning and Reduced Order Modelsphysics.comp-ph
This paper accelerates inverse solutions for PDEs using ML and ROMs.
problem Efficiently solving inverse problems governed by PDEs with many forward model solves.
method Combining ML with ROMs to improve accuracy and speed.
result ML-enhanced ROMs accelerate inverse problem solving.
RAPTOR-GEN accelerates digital twin development for biopharmaceuticals.
problem Lack of agility in rapid, on-demand production of biotherapeutics due to bioprocess complexity.
method Bayesian learning framework based on a multi-scale probabilistic knowledge graph (pKG) and stochastic differential equations (SDE).
result RAPTOR-GEN accelerates intelligent digital twin development from sparse and heterogeneous experimental data.
PERK speeds up MRI parameter estimation without needing a dictionary.
problem Efficiently estimating MRI parameters without a dictionary.
method Regression with kernels using prior distributions and nonlinear MR signal model.
result PERK is at least 23 times faster than grid search for estimation.