The paper optimizes neural network inference on mobile GPUs.
problem Limited computing power and thermal constraints on mobile CPUs.
method Leverage mobile GPUs for neural network inference.
result Real-time inference of deep neural networks on Android and iOS devices.
The realized stochastic volatility (RSV) model that utilizes the realized volatility as additional information has been proposed to infer volatility of financial time series. We consider the Bayesian inference of the RSV model by the Hybrid Monte Carlo (HMC) algorithm. The HMC algorithm can be parallelized and thus per…
NetFuse merges different DNN models with varying weights for faster inference.
problem Inference speed of DNN models with different weights cannot be improved using existing techniques.
method NetFuse merges models with the same architecture but different weights and inputs, replacing operations with more general ones.
result NetFuse can speed up DNN inference time up to 3.6x on a NVIDIA V100 GPU.
GPyTorch accelerates GP inference using GPU hardware.
problem Inefficient GP inference tools on modern hardware.
method Blackbox Matrix-Matrix (BBMM) inference with GPU acceleration.
result Significant speedup in GP inference and approximations.
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.
Binarized CNNs improve GPU inference efficiency on resource-constrained devices.
problem Efficient inference on resource-constrained devices for image classification.
method Binarization of weights and computations in CNNs, implemented on GPUs.
result 7.4X speedup with 4.4% accuracy loss on embedded GPU platforms.
SparseRT accelerates sparse computations on GPUs for deep learning inference.
problem Efficiently handling unstructured sparsity patterns on GPUs for deep learning.
method SparseRT, a code generator that leverages unstructured sparsity for accelerating sparse linear algebra operations.
result Geometric mean speedups of 3.4x at 90% sparsity and 5.4x at 95% sparsity for 1x1 convolutions and fully connected layers.
New algorithm reduces costs and latency for large language model inference.
problem Optimizing inference costs and latency for large language models with GPU constraints.
method Formulated as an online scheduling problem with endogenous memory growth, introduced fluid model and WAIT algorithms.
result Reduced costs and latency, especially in near-overloaded and overloaded regimes.
Nested Slice Sampling accelerates Nested Sampling for GPU acceleration.
problem Challenging inference for complex, multimodal targets.
method Vectorized Nested Slice Sampling using Hit-and-Run Slice Sampling.
result NSS maintains accurate evidence estimates and high-quality posterior samples, robust on multimodal problems.
BLISS detects and separates astronomical sources quickly and accurately.
problem Detecting and separating overlapping astronomical sources in large images.
method Bayesian Light Source Separator (BLISS) using deep generative models and variational inference.
result BLISS can process megapixel images in seconds and produce highly accurate catalogs.
The paper parallelizes HMM inference for efficient long-term computations.
problem Efficiently computing inference in long-term hidden Markov models.
method Parallelization using associative elements and operators for sum-product and max-product algorithms.
result The proposed parallel algorithms are computationally efficient for long time horizons.
It is time-consuming and error-prone to implement inference procedures for each new probabilistic model. Probabilistic programming addresses this problem by allowing a user to specify the model and having a compiler automatically generate an inference procedure for it. For this approach to be practical, it is important…
ChEES-HMC improves SMC samplers' efficiency and speed.
problem Efficiently sampling from complex posterior distributions.
method Incorporating ChEES-HMC into SMC samplers.
result ChEES-HMC outperforms NUTS in speed and efficiency.
NO-BEARS algorithm speeds up gene network inference from transcriptomic data.
problem Constructing accurate gene regulatory networks from transcriptomic data.
method NO-BEARS algorithm, based on NOTEARS, with new constraint and polynomial regression loss.
result Significantly reduced computational time and improved accuracy in inferring gene regulatory networks.
New software package for scalable DPMM inference on large datasets.
problem Scalability and practical adoption of Dirichlet Process Mixture Models.
method Efficient distributed sampling-based inference on CPUs and GPUs.
result Significant speedups and fitting of larger datasets.
LDTA expands LDA's topic modeling capacity with tree-structured priors.
problem Limited expressiveness of Dirichlet priors in LDA for complex topic relationships.
method Introduces Latent Dirichlet-Tree Allocation (LDTA) with Dirichlet-Tree (DT) priors, and develops universal mean-field variational inference and Expectation Propagation.
result LDTA enables expressive, tree-structured priors over topic proportions, expanding modeling capacity of LDA.
Investigates the impact of batch size on GPU and TPU performance.
problem Optimizing performance of GPUs and TPUs during training and inference phases.
method Investigated the impact of batch size on performance of GPUs and TPUs using standard MNIST and Fashion-MNIST datasets.
result Significant speedup was achieved even with low-scale usage of TPUv2 units, up to 10x for training and 2x for prediction.
The paper proposes an efficient method to scale Bayesian inference for mixed multinomial logit models to very large datasets.
problem Efficiency in Bayesian inference for mixed multinomial logit models on large datasets.
method Amortized Variational Inference with stochastic backpropagation, automatic differentiation, and GPU acceleration.
result The proposed method achieves significant computational speedups over traditional methods for large datasets.
New method ensures consistent inference across different tensor parallel sizes for large language models.
problem Non-deterministic inference in large language models due to inconsistent reduction orders across GPUs.
method Tree-Based Invariant Kernels (TBIK) that align intra- and inter-GPU reduction orders through a unified hierarchical binary tree structure.
result Bit-wise identical results across different tensor parallel sizes for RL training.
New framework quantifies uncertainty in flexible density-based clustering.
problem Uncertainty quantification in clustering with non-parametric density estimation.
method Martingale posterior distributions and density-based clustering.
result Efficient GPU-compatible inference on clustering structures with uncertainty.
DistShap parallelizes GNN explanation for large graphs.
problem Computational expense in attributing GNN predictions to specific edges or features.
method Distributed Shapley values across multiple GPUs for scalable GNN explanations.
result DistShap outperforms existing methods and scales to models with millions of features.
New method improves Kalman filtering and smoothing for large state spaces.
problem High computational cost and uncertainty in large-scale Kalman filtering.
method Probabilistic numerical method leveraging GPU acceleration and tunable trade-off.
result Mitigates scaling issues and provides more accurate uncertainty estimates.
Efficient non-uniform quantizer improves CNN performance on FPGA.
problem Improving CNN performance on low-power systems like mobile devices.
method Custom hardware-friendly non-uniform quantizer for parameters and activations using a single scale integer representation.
result Little degradation in accuracy on CIFAR-10 and CIFAR-100 datasets.
We accelerate Bayesian inference for neutrino physics experiments by 100-60x.
problem Complex posterior geometries in multi-dimensional parameter spaces.
method GPU acceleration, automatic differentiation, neural-network-guided reparameterization.
result Significant performance improvements in Bayesian inference for direct detection experiments.
New hybrid model reduces MILP solver time by up to 26%.
problem Improving CPU-based MILP solver efficiency.
method Combines GNN and MLP for efficient CPU-based branching.
result Up to 26% reduction in solver running time compared to state-of-the-art methods.
New GPU algorithm boosts machine learning with larger datasets.
problem Limited GPU memory restricts training data size.
method Out-of-core GPU gradient boosting algorithm.
result Training larger datasets on GPUs without accuracy loss.
Massively parallel architectures such as the GPU are becoming increasingly important due to the recent proliferation of data. In this paper, we propose a key class of hybrid parallel graphlet algorithms that leverages multiple CPUs and GPUs simultaneously for computing k-vertex induced subgraph statistics (called graph…
STAND-DA improves AD in DA target domains with limited data.
problem Statistical validity of AD after DA with limited data.
method Selective Inference framework for GPU-accelerated p-value computation. result Valid p-values and controlled false positive rate. Train a lightweight carry-on model on existing LLMs for faster customization.
problem Customizing large language models for specific tasks is computationally expensive.
method Train an additional branch of transformer blocks on the final-layer embedding of pretrained LLMs, then merge them with a carry-on module.
result Training a 100M carry-on layer requires less than 1GB GPU memory, making it scalable and affordable.
A new model decomposes market variability into interpretable components.
problem Understanding the factors driving market variability and predicting future movements.
method H-SGDLM framework with HAR-RV model for GPU-scalable multivariate volatility estimation.
result Superior performance in predicting large moves and longer-term market variability.
Probabilistic modeling is a powerful approach for analyzing empirical information. We describe Edward, a library for probabilistic modeling. Edward's design reflects an iterative process pioneered by George Box: build a model of a phenomenon, make inferences about the model given data, and criticize the model's fit to …
CuLE accelerates reinforcement learning on GPUs.
problem Limited CPU-GPU communication bandwidth in Atari Learning Environment.
method CUDA port of ALE, leveraging GPU parallelization and direct frame rendering.
result Up to 155M frames per hour on a single GPU, accelerating reinforcement learning.
AcceleratedLiNGAM speeds up causal discovery methods for large datasets.
problem Slow causal discovery methods for large-scale datasets.
method Parallelized LiNGAM method with GPU acceleration.
result Up to 32-fold speed-up on benchmark datasets.
Exact GPs trained on over a million points in under 2 hours.
problem Computational limitations of exact Gaussian processes for large datasets.
method Multi-GPU parallelization and linear conjugate gradients for kernel matrix multiplication.
result Exact GPs can be trained on over a million points in less than 2 hours.
XGBoost accelerates machine learning on GPUs.
problem Training large datasets efficiently on GPUs.
method Multi-GPU gradient boosting with data compression and end-to-end GPU parallelism.
result Processed 115 million instances in 3 minutes.
GPflow is a Gaussian process library that uses TensorFlow for its core computations and Python for its front end. The distinguishing features of GPflow are that it uses variational inference as the primary approximation method, provides concise code through the use of automatic differentiation, has been engineered with…
Extends GENO framework for GPU optimization of constrained ML problems.
problem Constrained optimization in classical machine learning.
method Extends GENO framework to GPU optimization, specifying problems in a modeling language.
result Solvers on GPU outperform state-of-the-art approaches by several orders of magnitude.
GPU computing has become popular in computational finance and many financial institutions are moving their CPU based applications to the GPU platform. Since most Monte Carlo algorithms are embarrassingly parallel, they benefit greatly from parallel implementations, and consequently Monte Carlo has become a focal point …
Pyro enables scalable AI models using probabilistic programming.
problem Developing complex probabilistic models for large datasets.
method Stochastic variational inference, PyTorch, Poutine.
result Pyro supports scalable AI models with high-dimensional data.
DoRA improves adaptation efficiency for large models by factoring norms and fusing kernels.
problem High-rank DoRA is computationally expensive and infeasible on common GPUs.
method Factored norms and fused Triton kernels to reduce memory and speed up computation.
result Fused implementation is up to 2.0x faster for inference and 1.9x faster for gradient computation.
Python package for fast simulation-based inference.
problem Intractable likelihood functions in Bayesian inference.
method Uses neural networks as surrogate models for Bayesian inference.
result Highly efficient and user-friendly for constructing SBI estimators.
GPU speeds up derivatives sensitivity computation for Heston model options.
problem Efficient computation of option Greeks under the Heston model.
method Implemented exact simulation and novel Milstein discretisation methods on GPU.
result GPU speeds up Greeks computation up to 200x compared to CPU methods.
FPGAs accelerate DNNs with binarized weights, improving power and speed.
problem Power and speed limitations of GPU-accelerated DNNs.
method Binarized neural networks on FPGAs using OpenCL.
result Near state-of-the-art performance with >16x power savings.
Energy savings for DNN inference on resource-constrained devices.
problem Energy efficiency in deep learning inference for constrained devices.
method Efficiently searches through equivalent DNN graphs to find the one with the least execution cost.
result Achieves 24% energy savings with minimal performance impact.
AriaNN enables private deep learning with minimal interaction and reduced key sizes.
problem Private deep learning with minimal interaction and reduced key sizes.
method Semi-honest 2-party computation protocol with function secret sharing, optimized primitives for neural network operations.
result Efficient private comparison for ReLU operations with reduced key size and improved 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.
JAXFit speeds up curve fitting on GPUs.
problem Nonlinear least squares curve fitting problems.
method Trust region method on GPU with automatic differentiation.
result Significantly faster than CPU and other GPU libraries.
A new parallel algorithm speeds up Hawkes process estimation.
problem Slow maximum likelihood estimation for Hawkes processes.
method Parallel prefix scan for sparse transition matrices.
result Massive speedup with O(N/P) complexity.