arXiv research

A new sampling method called Restart improves both speed and quality of generative processes.

Unified model improves sampling speed and quality.

Improves sampling speed of ARM models without losing accuracy.

Adaptive sampling improves graph diffusion models by maintaining uniform information speed.

FastForest boosts Random Forest speed by 24%.

Accurately modeling traffic speeds is a fundamental part of efficient intelligent transportation systems. Nowadays, with the widespread deployment of GPS-enabled devices, it has become possible to crowdsource the collection of speed information to road users (e.g. through mobile applications or dedicated in-vehicle dev…

Paper accelerates diffusion models, improving sampling speed.

WeSpeR speeds up non-linear shrinkage for high-dimensional weighted covariance.

Improved language generation with faster sampling speed.

Non-autoregressive method speeds up protein folding prediction 23 times.

HollowFlow speeds up likelihood evaluation for large-scale models.

Quantum algorithms speed up reinforcement learning policies in large state-action spaces.

A new algorithm speeds up elliptical slice sampling for truncated multivariate normals.

Study uses CNNs to upscale wind speed data from 100 km to 3 km, improving subgrid-scale variability.

Paper proposes a modified uncertainty sampling method to speed up preference learning from noisy humans.

In this technical report, we consider an approach that combines the PPO objective and K-FAC natural gradient optimization, for which we call PPOKFAC. We perform a range of empirical analysis on various aspects of the algorithm, such as sample complexity, training speed, and sensitivity to batch size and training epochs…

Adaptive workflow combines fast amortized inference with MCMC for many datasets.

LGES speeds up causal discovery while maintaining accuracy.

FedSARSA converges with heterogeneous agents, achieving linear speed-up.

Preconditioned NFs speed up sampling from complex posterior distributions in inverse problems.

In this paper we propose new techniques to sample arbitrary third-order tensors, with an objective of speeding up tensor algorithms that have recently gained popularity in machine learning. Our main contribution is a new way to select, in a biased random way, only $O(n^{1.5}/ε^2)$ of the possible $n^3$ elements while s…

DistillKac generates images quickly using damped wave equations.

The convergence speed of stochastic gradient descent (SGD) can be improved by actively selecting mini-batches. We explore sampling schemes where similar data points are less likely to be selected in the same mini-batch. In particular, we prove that such repulsive sampling schemes lowers the variance of the gradient est…

Regularized SB process speeds up generative modeling.

Matrix multiplication is a fundamental building block for large scale computations arising in various applications, including machine learning. There has been significant recent interest in using coding to speed up distributed matrix multiplication, that are robust to stragglers (i.e., machines that may perform slower …

New method speeds up diffusion models without requiring complex assumptions.

Dynamic sample pruning speeds up spatio-temporal forecasting models.

New algorithm speeds up diffusion model sampling 4-14 times.

New algorithm speeds up sampling from log-concave distributions over polytopes.

A new Metropolis-Hastings algorithm uses Gaussian Processes to speed up sampling from complex models.

EiGLasso speeds up sparse Kronecker-sum covariance estimation.

Paper reinterprets ARP algorithm and improves its analysis and speed.

Discrete noise improves graph generation quality and speed.

Data-driven modeling increasingly requires to find a Nash equilibrium in multi-player games, e.g. when training GANs. In this paper, we analyse a new extra-gradient method for Nash equilibrium finding, that performs gradient extrapolations and updates on a random subset of players at each iteration. This approach prova…

Proposes faster neural network learning by using subsets of training data.

UD-SGD analysis shows efficient sampling by a few agents can outperform others.

Improved convergence in deep learning networks via gradient transformation.

We propose a generic Markov Chain Monte Carlo (MCMC) algorithm to speed up computations for datasets with many observations. A key feature of our approach is the use of the highly efficient difference estimator from the survey sampling literature to estimate the log-likelihood accurately using only a small fraction of …

We analyse the learning performance of Distributed Gradient Descent in the context of multi-agent decentralised non-parametric regression with the square loss function when i.i.d. samples are assigned to agents. We show that if agents hold sufficiently many samples with respect to the network size, then Distributed Gra…

A recently introduced Importance Sampling strategy based on a least squares optimization is applied to the Monte Carlo simulation of Libor Market Models. Such Least Squares Importance Sampling (LSIS) allows the automatic optimization of the sampling distribution within a trial class by means of a quick presimulation al…

Hessian-free training has become a popular parallel second or- der optimization technique for Deep Neural Network training. This study aims at speeding up Hessian-free training, both by means of decreasing the amount of data used for training, as well as through reduction of the number of Krylov subspace solver iterati…

A new algorithm speeds up CP decomposition for large tensors.

Efficiently trains forward processes to minimize generative trajectories curvature.

VADD enhances discrete diffusion models by capturing inter-dimensional correlations, improving sample quality.

Few-step protein backbone generators reduce sampling time by over 20x.

Optimal sampling reduces power grid data analysis costs.

A scalable version of MADD improves big-data classification speed.

SeqRF straightens generative model flows to speed up sampling.