Speeds up training and inference by pruning entire channels before training.
problem Training and inference speed in deep neural networks.
method Structured pruning applied before training, focusing on removing entire channels and hidden units.
result 2x speedup in training and 3x speedup in inference.
Non-autoregressive method speeds up protein folding prediction 23 times.
problem Generating protein sequences with higher order interactions.
method Discrete diffusion conditioned on 3D structure using ProteinMPNN.
result 23 times speed up in inference without performance loss.
Adaptive workflow combines fast amortized inference with MCMC for many datasets.
problem Trade-off between computational speed and sampling accuracy in Bayesian inference.
method Adaptive workflow integrating amortized inference and MCMC with principled diagnostics.
result Efficiency gains with high posterior quality on tens of thousands of datasets.
New method speeds up deep neural networks inference.
problem Inference speed of deep neural networks.
method Maximum volume algorithm for reduced-order modeling.
result Convolutional layers can be replaced with smaller fully-connected layers with minimal accuracy loss.
We introduce the SaaS Algorithm for semi-supervised learning, which uses learning speed during stochastic gradient descent in a deep neural network to measure the quality of an iterative estimate of the posterior probability of unknown labels. Training speed in supervised learning correlates strongly with the percentag…
Structural-Jump-LSTM speeds up reading by skipping and jumping text.
problem Sequential inference in RNNs makes reading time linearly dependent on input length.
method Introduces a novel LSTM model with agents for skipping and jumping text.
result Structural-Jump-LSTM achieves best FLOP reduction and maintains or improves accuracy.
Improves sampling speed of ARM models without losing accuracy.
problem Slow sampling from ARMs.
method Predictive sampling algorithm using ARM fixed-point iteration and learned forecasting modules.
result Significant improvements in sampling speed and efficiency.
This paper speeds up iterative GP inference with warm starting.
problem Improving scalability of Gaussian process inference.
method Warm starting sequential posteriors using known solutions.
result Significant speed-ups and improved Bayesian optimisation performance.
Loihi neuromorphic chip outperforms conventional hardware in keyword spotting efficiency.
problem Benchmarking keyword spotting efficiency on neuromorphic hardware.
method Comparative analysis of a two-layer neural network trained to recognize a single phrase on Intel's Loihi neuromorphic chip and conventional hardware devices.
result Loihi outperforms conventional hardware on energy cost per inference for this keyword spotting application.
A new framework speeds up Bayesian inference in probabilistic programs.
problem Efficient Bayesian inference in complex probabilistic programs.
method Embeds a sampler within a refined variational posterior approximation, using automatic differentiation for parameter tuning.
result Significantly speeds up mixing time and improves efficiency in various probabilistic program tasks.
Kaleidoscope matrices improve model quality and inference speed.
problem Choosing structured linear transformations for efficiency and accuracy.
method Introduce kaleidoscope matrices that can capture any structured matrix with near-optimal space and time complexity. Learn these matrices automatically within end-to-end pipelines.
result Kaleidoscope matrices can improve model quality and inference speed.
ADVI speeds up Bayesian inference for bridge regression models.
problem Slow MCMC for large datasets in bridge regression.
method Automatic Differentiation Variational Inference (ADVI) for Bayesian inference.
result ADVI implementation speeds up inference for large datasets.
Warm-start strategies speed up GP inference by 19x.
problem Efficient sequential inference in Gaussian processes.
method Three warm-start strategies exploiting smaller linear systems.
result Warm-starting achieves up to 19x speed-up in convergence.
One-bit quantization improves inference speed for Random Features models.
problem Efficient inference on resource-constrained devices.
method Analysis of one-bit quantization in Random Features model.
result Asymptotically, quantizing weights except the last incurs no loss in generalization error.
Stochastic VB improves nonlinear model inference speed and accuracy.
problem Bayesian inference of nonlinear models from noisy data.
method Stochastic Variational Bayesian (VB) inference for nonlinear models.
result Stochastic VB achieves comparable parameter recovery to analytical solution but is faster.
A new GP model uses spherical harmonics for faster inference.
problem Efficiently fitting large datasets with Gaussian processes.
method Sparse Gaussian processes with spherical harmonic features.
result Significant speed-up in inference for large datasets.
We propose and evaluate new techniques for compressing and speeding up dense matrix multiplications as found in the fully connected and recurrent layers of neural networks for embedded large vocabulary continuous speech recognition (LVCSR). For compression, we introduce and study a trace norm regularization technique f…
PoWER-BERT speeds up BERT inference by eliminating redundant word-vectors.
problem Improving BERT inference speed without sacrificing accuracy.
method Eliminating redundant word-vectors using a self-attention-based significance measure and learning the number of vectors to eliminate.
result Up to 4.5x reduction in inference time with <1% loss in accuracy on GLUE benchmark.
DeepRV accelerates spatiotemporal inference using neural priors.
problem Intractable scaling of Gaussian Processes for large datasets.
method Neural-network surrogate replacing GP prior sampling with O(N2) complexity. result DeepRV achieves highest fidelity to exact GPs while significantly speeding up inference.
Gaussian processes (GP) are attractive building blocks for many probabilistic models. Their drawbacks, however, are the rapidly increasing inference time and memory requirement alongside increasing data. The problem can be alleviated with compactly supported (CS) covariance functions, which produce sparse covariance ma…
Stochastic variational inference (SVI) employs stochastic optimization to scale up Bayesian computation to massive data. Since SVI is at its core a stochastic gradient-based algorithm, horizontal parallelism can be harnessed to allow larger scale inference. We propose a lock-free parallel implementation for SVI which a…
New algorithm speeds up Bayesian UQ for high-dimensional inverse problems.
problem Computational inefficiency in Bayesian inference for high-dimensional inverse problems.
method Deep neural network-based autoencoder for dimension reduction and emulation phase.
result Computational efficiency up to three orders of magnitude with scalable Bayesian UQ.
Paper improves GNN inference speed and memory usage.
problem Scalability issues in GNNs during inference.
method Graph coarsening techniques for faster inference.
result Significant reduction in inference time and memory usage.
Density-Regression improves deep uncertainty estimation with faster inference.
problem Efficient uncertainty estimation under distribution shifts with modern deep models.
method Leverages density function for fast inference and distance-aware feature space.
result Density-Regression achieves competitive uncertainty estimation performance.
Variational inference has experienced a recent surge in popularity owing to stochastic approaches, which have yielded practical tools for a wide range of model classes. A key benefit is that stochastic variational inference obviates the tedious process of deriving analytical expressions for closed-form variable updates…
New methods speed up Bayesian experimental design.
problem Difficulty in estimating expected information gain.
method Amortized variational inference for fast EIG estimation.
result Significant gains in speed and accuracy.
Paper speeds up Gaussian process inference using Matérn kernels.
problem Efficiently performing Gaussian process inference for large datasets.
method Exact Matérn kernel decomposition into empirical cumulative distribution functions, combined with divide-and-conquer approach.
result The proposed algorithm significantly speeds up Gaussian process inference for low-dimensional problems with hundreds of thousands of data points.
New algorithm speeds up large-scale statistical inference.
problem Efficiently solving large-scale mean-field variational inference problems.
method Developed a novel primal-dual algorithm (PD-VI) and a block-preconditioned extension (P2D-VI) for mean-field variational inference. result PD-VI and P2D-VI achieve faster convergence and better solution quality compared to existing methods. Fast variational Bayes methods improve geospatial data analysis speed and accuracy.
problem Inaccurate and slow variational Bayes methods for large geospatial data.
method Combination of calculus of variations, closed-form gradient updates, and linear response corrections.
result Comparable accuracy to spNNGP with reduced computational costs and faster speed.
Delta-AI speeds up inference in sparse PGMs by local credit assignment.
problem Efficient inference in sparse probabilistic graphical models.
method Local credit assignment in agent's policy learning objective.
result Trained sampler recovers marginals and conditional distributions.
DARC learns resource-efficient models by replacing expensive components with cheaper ones.
problem Resource constraints at inference time are more severe than at training time.
method Combines model compression and architecture search to learn resource-efficient models.
result Improves inference speed and memory footprint with minimal accuracy loss.
Deep learning and genetic algorithms speed up cosmological Bayesian inference.
problem Substantial computational demands in Bayesian inference for cosmological parameter estimation.
method Deep learning using feedforward neural networks to approximate likelihood functions dynamically, optimized with genetic algorithms.
result Significant speed-up in Bayesian inference process for cosmological models and datasets.
ELM speeds up financial machine learning tasks.
problem Efficiently solving time-sensitive financial tasks with machine learning.
method Single-layer neural networks with random initialization and convex optimization.
result ELM achieves significant computational efficiency in financial applications.
Preconditioned NFs speed up sampling from complex posterior distributions in inverse problems.
problem Sampling from posterior distributions of inverse problems with expensive forward operators.
method Preconditioning a conditional normalizing flow (NF) to speed up training.
result Significant speed-ups achieved compared to training NFs from scratch.
Simulation-based inference speeds up gravitational wave data analysis.
problem High-dimensional parameter spaces and complex noise in gravitational wave data.
method Simulation-based inference methods using machine learning techniques.
result Simulation-based inference methods improve speed over traditional methods.
New algorithm speeds up SVAR inference for large datasets.
problem Inference in sign-identified SVARs for big data.
method Elliptical slice within Gibbs sampler for computational efficiency.
result Algorithm delivers posterior distribution and is well-defined.
We introduce incremental variational inference and apply it to latent Dirichlet allocation (LDA). Incremental variational inference is inspired by incremental EM and provides an alternative to stochastic variational inference. Incremental LDA can process massive document collections, does not require to set a learning …
Researchers use Gaussian Process Regression to improve accuracy of a low-cost hot-wire anemometer.
problem Improving accuracy of low-cost hot-wire anemometers in varying temperatures.
method Probabilistic calibration using Gaussian Process Regression.
result The method provides good performance in estimating actual wind speeds, including uncertainty.
New method improves Bayesian inference for large models.
problem Bayesian inference in large-scale models like neural networks.
method Non-parametric variational approximation with a modified Langevin algorithm.
result Improves convergence speed and accuracy compared to existing methods.
Improved Kalman filtering with hierarchical variational approach.
problem Inconsistent process covariance estimation and slow convergence speed in traditional variational Kalman filtering.
method Introducing a surrogate variable for process-noise-free state, reformulating CAVI, and sliding-window hyperparameter estimation.
result Enhanced convergence speed and superior estimation accuracy compared to existing methods.
RVI accelerates encoderless VI for faster convergence.
problem Slow convergence in encoderless VI methods.
method Introduces Relay Variational Inference (RVI) for faster learning.
result RVI outperforms existing methods in convergence speed and performance.
We present a general method for deriving collapsed variational inference algo- rithms for probabilistic models in the conjugate exponential family. Our method unifies many existing approaches to collapsed variational inference. Our collapsed variational inference leads to a new lower bound on the marginal likelihood. W…
New method speeds up inference for non-conjugate Gaussian processes.
problem Inference for non-conjugate Gaussian processes is slow and unreliable.
method Automated augmented conjugate inference method that constructs auxiliary variables to make the model conditionally conjugate.
result Our method is up to two orders of magnitude faster and more robust than existing methods.
A new Metropolis-Hastings algorithm uses Gaussian Processes to speed up sampling from complex models.
problem Sampling from computationally expensive probabilistic models.
method Two-stage Metropolis-Hastings algorithm with a Gaussian Process surrogate model.
result The approach learns the target distribution while sampling, eliminating the need for pre-training.
Paper speeds up neural language model inference by 20x for top-k word prediction.
problem Slow inference speed of neural language models on mobile devices.
method Introduced a screening model using Gumbel softmax to approximate softmax layer.
result Achieved 20.4x speedup with 98.9% precision@1 and 99.3% precision@5 for German to English translation.
SEISM tests neural network features for regulatory genomics.
problem Testing neural network features for regulatory genomics.
method Selective inference procedure for sequence motifs.
result Sampling under specific parameters characterizes composite null hypothesis.
PyVBMC speeds up Bayesian inference for expensive models in Python.
problem Efficient Bayesian inference for computationally expensive models.
method Variational Bayesian Monte Carlo (VBMC) algorithm.
result PyVBMC provides a flexible and efficient method for parameter estimation and model assessment.
Improves SVGP methods for faster and more accurate Gaussian process inference.
problem Efficient non-conjugate Gaussian process inference.
method Dual parameterization of SVGP methods using site parameters.
result Faster and more accurate inference with tighter evidence lower bound.