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.

169,341 papers · 148 categories

Trend · papers per month

2875748611,148 · Jun 202019922001200920182026
48 results for reduced computation time

Paper optimizes distributed learning by reducing gradient computation time.

problem Efficiently compute gradients in distributed learning tasks.
method Recursive polynomial constructions for coding across data subsets and vector components.
result Optimal tradeoff between computation load, straggler tolerance, and communication cost achieved.

Reduced reservoir size for faster edge computing.

problem Efficiently reducing computational resources for reservoir computing.
method Concatenating past or drifting states of the reservoir to the output layer.
result Reduced reservoir size up to one tenth without significant error increase.

Channel gating reduces CNN computation cost by skipping ineffective feature regions.

problem Reducing computation cost in CNNs while maintaining accuracy.
method Dynamic, fine-grained pruning scheme that identifies and skips computation on ineffective feature regions.
result 2.7-8.0x reduction in FLOPs and 2.0-4.4x reduction in memory accesses with minimal accuracy loss.

Improves distributed SGD convergence speed with reduced computation load.

problem Mitigating stragglers in distributed SGD to speed up convergence.
method Modeling communication and computation times, adapting number of workers and computation load dynamically.
result Significantly reduces computation load while improving convergence speed.

This paper optimizes SMPC for neural network inference, reducing memory and time.

problem Memory and time constraints in secure neural network inference.
method Implemented ABY2.0 protocol, optimized memory usage, and used a helper node.
result MNIST inference reduced from 8.03 GB RAM and 200s to 0.2 GB RAM and 32s.

A new method reduces computational time for source separation and classification.

problem High computational complexity and unsatisfactory source classification accuracy in MVAE.
method Integrates an auxiliary classifier VAE to reduce computational time and improve classification accuracy.
result fMVAE achieved comparative source separation performance and 80% source classification accuracy while reducing computational time by 93%.

New algorithm reduces BO's computational burden for expensive experiments.

problem BO's computational cost is often ignored in practice, making it inefficient for time-consuming experiments.
method Introduces Dimension Scheduling Algorithm (DSA) to optimize BO for many experiments.
result DSA finds good solutions faster and reduces computation time compared to traditional BO.

hi-RF method improves large-scale multi-class data classification with less computational time.

problem Dynamic growth of data and classes poses challenges to traditional classification methods.
method hi-RF is an incremental learning method that replaces or updates trees in random forest adaptively.
result hi-RF achieves comparable precision with significantly reduced computational time.

Layer normalization speeds up training of neural networks.

problem Training deep neural networks is computationally expensive.
method Layer normalization computes mean and variance from all summed inputs in a layer per training case, unlike batch normalization which uses mini-batch.
result Layer normalization stabilizes hidden state dynamics in recurrent networks and reduces training time.

NGRC shows numerical instabilities with short lags and high-degree polynomials.

problem Numerical instabilities in NGRC feature matrix.
method Combining numerical linear algebra and dynamical systems theory, we study feature matrix conditioning. We evaluate different numerical algorithms for solving the regularized least-squares problem.
result SVD-based training achieves accurate forecasts without regularization, preferable for short lags and high-degree polynomials.

Efficiently reduces training and inference costs by dynamically selecting important channels.

problem Reducing memory and computational demands for neural network training and inference.
method Integrates pruning into training by selecting only highly salient channels for execution, using combinatorial upper confidence bound algorithm.
result Reduces computational cost up to 4x and parameter count up to 9x.

FastGAT reduces GNN computation time by 10x using graph sparsification.

problem High computational burden in attention-based GNNs.
method Spectral sparsification to generate optimal graph pruning.
result Per-epoch time is almost linear in graph nodes, reducing computational time by up to 10x.

A new method reduces the computational time for pricing financial derivatives with complex models.

problem Pricing financial derivatives with a large number of variables.
method Chebyshev reduced basis function for polynomial interpolation and hierarchical orthogonalization.
result A significant reduction in computational time for pricing various financial contracts.

New strategies reduce FL's impact on client resources, enabling larger models and more users.

problem Communication bottleneck in Federated Learning on heterogeneous edge networks.
method Lossy compression and Federated Dropout to reduce client-to-server communication and local computation.
result Up to 14x reduction in server-to-client communication, 1.7x reduction in local computation, and 28x reduction in upload communication.

New framework reduces factorisation model run time by exploiting sparse vector geometry.

problem Inefficient inner product computations over large sparse vectors in real-time applications.
method Geometry-aware permutation maps on a tessellated unit sphere for sparse vector embeddings.
result Significant reduction in run time with minimal accuracy loss.

LightOn OPUs accelerate randomized numerical linear algebra, reducing computational costs.

problem Computational bottleneck in randomization step for large-scale linear algebra.
method Near constant-time linear random projections from LightOn OPUs.
result Significant acceleration of RandNLA algorithms with negligible precision loss.

Paper proposes a log-domain training method to reduce neural network complexity.

problem High computational complexity in training deep neural networks limits real-time training.
method End-to-end training and inference scheme using approximate logarithmic operations in the log-domain.
result 16-bit log-based training achieves within 1% accuracy of floating-point baselines.

Structured sparsity improves deep neural networks for real-time applications.

problem High computational complexity and memory access issues in deep learning.
method Structured sparsity at various scales (channel, kernel, intra kernel) using particle filtering for importance weighting.
result Significant reduction in network size and storage requirements for real-time applications.

A new method reduces feature screening cost from O(np)O(np) to O(np)O(\sqrt{n}p).

problem Eliminating non-informative features in ultrahigh-dimensional datasets.
method Adaptive subsampling method based on multi-armed bandit problem.
result The proposed method retains sure screening property and comparable performance to SIS.

Reducing neural network training time by using smaller, representative datasets.

problem Long training times for neural networks.
method Topology-based representative datasets, measured by persistence diagrams.
result Neural network accuracy on representative datasets is similar to original datasets for perceptrons and mean squared error.

Improved BLS by reducing pseudoinverse complexity for added inputs.

problem High computational complexity in pseudoinverse for incremental learning.
method Used inverse of a sum of matrices to reduce matrix inversion size.
result Significant reduction in computational complexity (1.24 - 1.30 speedups).

Proposes a method to forecast dependencies between thousands of time series.

problem Computational and numerical difficulties in estimating high-dimensional covariance matrices.
method Combines RNN and Gaussian copula process with low-rank covariance structure.
result Significant accuracy improvements over state-of-the-art baselines.

A distributed framework for reducing high-dimensional matrix-variate time series data.

problem Reducing dimensionality of high-dimensional, heterogeneous matrix-variate time series data.
method Data partitioning, distributed two-dimensional tensor PCA, aggregation, final PCA, factor matrix computation.
result Preserves latent matrix structure, improves computational efficiency and information utilization.

TinyLSTMs reduces speech enhancement model size and latency for hearing aids.

problem Large RNNs limit practical deployment in hearing aid hardware.
method Model compression techniques (pruning, integer quantization, state update skipping) for RNN speech enhancement.
result Reduction in model size and operations by 11.9imes imes and 2.9imes imes, respectively, without perceptual degradation.

Time-varying parameters are shown to be ridge regressions, simplifying computations and tuning.

problem Capturing structural change in economic data.
method Ridge regression approach, including cross-validation for tuning, and extensions for sparsity and reduced-rank restrictions.
result The method efficiently estimates large numbers of time-varying parameters, demonstrated with Canadian monetary policy data.

Paper reduces AI complexity with pre-defined sparsity and hardware acceleration.

problem Reduction of computational and storage complexity in neural networks.
method Pre-defined sparsity and hardware acceleration architecture.
result Significant reduction in storage and computational complexity (5X+ reduction) without significant performance loss.

Paper proposes efficient BNN inference flow to reduce computation and memory costs.

problem High computation complexity in Bayesian Neural Networks (BNNs) limits deployment in power-constrained systems.
method Feature decomposition and memorization strategy to reduce computations and a memory-friendly computing framework to reduce memory overhead.
result Reduces computation by about half and energy consumption by 73% with 14% area overhead.