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.
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…
Using Intel's Loihi neuromorphic research chip and ABR's Nengo Deep Learning toolkit, we analyze the inference speed, dynamic power consumption, and energy cost per inference of a two-layer neural network keyword spotter trained to recognize a single phrase. We perform comparative analyses of this keyword spotter runni…
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.
Recurrent neural networks (RNNs) can model natural language by sequentially 'reading' input tokens and outputting a distributed representation of each token. Due to the sequential nature of RNNs, inference time is linearly dependent on the input length, and all inputs are read regardless of their importance. Efforts to…
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…
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.
Autoregressive models (ARMs) currently hold state-of-the-art performance in likelihood-based modeling of image and audio data. Generally, neural network based ARMs are designed to allow fast inference, but sampling from these models is impractically slow. In this paper, we introduce the predictive sampling algorithm: a…
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…
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. In many learning situations, resources at inference time are significantly more constrained than resources at training time. This paper studies a general paradigm, called Differentiable ARchitecture Compression (DARC), that combines model compression and architecture search to learn models that are resource-efficient a…
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.
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.
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.
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.
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.
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 …
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…
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.
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.
Bayesian coresets improve scalable Bayesian inference.
problem Efficiently approximating posterior inference with a subset of data.
method Sparsity constrained optimization and accelerated optimization methods.
result Explicit convergence rate guarantees and superior performance compared to state-of-the-art.
This paper speeds up inference in large hierarchical models.
problem Inference in large hierarchical models is slow and difficult.
method Amortized variational inference with shared parameters.
result Amortized inference is as accurate as a full-rank Gaussian but much faster.
Enhances supervised learning speed with KT algorithm.
problem Speed up supervised learning tasks with minimal loss.
method Generalizes kernel thinning to supervised learning, combining NW and KRR with KT.
result KT-based estimators offer superior computational and statistical efficiency.
PGMax automates PGM inference on GPUs, improving quality and speed.
problem Efficient inference in complex discrete PGMs.
method Factor graph specification and loopy belief propagation in JAX.
result Higher-quality inference with up to 3x speedups.
New method speeds up lead-lag detection between asynchronous time series.
problem Slow inference of lead-lag networks between long time series.
method Derive asymptotic distribution of Transfer Entropy and introduce time-shifted time series.
result Statistically validated lead-lag networks between time series.
In this paper we present an algorithm for rapid Bayesian analysis that combines the benefits of nested sampling and artificial neural networks. The blind accelerated multimodal Bayesian inference (BAMBI) algorithm implements the MultiNest package for nested sampling as well as the training of an artificial neural netwo…