DLBricks automates DL benchmarking on CPUs, reducing effort and time.
problem Lack of representative and up-to-date DL benchmarks on CPUs.
method Decomposes DL models into runnable networks, leveraging layer repetition and auto-generation.
result Accurately estimates DL model performance and speeds up benchmarking time.
The study compares Fourier-based pricing methods, identifying the most efficient and accurate.
problem Comparing CPU effort and pricing biases of Fourier-based implementations.
method Numerical analysis of seven Fourier-based implementations, focusing on truncation and discretization errors.
result The multi-strike version of the COS method is notably faster, and the strike-optimized Carr Madan's formula is both faster and more accurate.
The past years have witnessed many dedicated open-source projects that built and maintain implementations of Support Vector Machines (SVM), parallelized for GPU, multi-core CPUs and distributed systems. Up to this point, no comparable effort has been made to parallelize the Elastic Net, despite its popularity in many h…
This paper proposes a hybrid CPU-GPU framework for faster graphlet computation.
problem Efficiently computing k-vertex induced subgraph statistics in large networks.
method Hybrid multi-core CPU-GPU framework, single GPU methods, and multi-GPU methods.
result 300 times faster than state-of-the-art methods.
Ansor generates high-performance tensor programs for deep learning.
problem Generating high-performance tensor programs for deep learning on various hardware platforms is challenging.
method Ansor uses a hierarchical representation of the search space, sampling programs, and evolutionary search with a learned cost model to find high-performance programs.
result Ansor improves deep neural network execution performance up to 3.8x on Intel CPU, 2.6x on ARM CPU, and 1.7x on NVIDIA GPU.
LoRA fine-tuning on CPUs without GPUs achieves comparable performance to GPU-based methods.
problem Limited computational resources for fine-tuning LLMs.
method Developed a CPU-efficient method to learn meta-operators for LoRA weights.
result LoRA adapters trained on CPUs outperform base models on downstream tasks.
The paper optimizes RF training by improving tree building algorithms and CPU optimizations.
problem Improving the training performance of Random Forest models on CPU architectures.
method Investigated and improved tree building algorithms (BFS, DFS, hybrid BFS-DFS) and proposed optimizations.
result The hybrid BFS-DFS algorithm outperforms both BFS and DFS, and is more robust.
AI methods often fail to outperform classical CPU-based solvers on Maximum Independent Set problems.
problem Comparing AI methods with classical CPU-based solvers on Maximum Independent Set problems.
method Comparison of AI methods (e.g., generative models, reinforcement learning) with classical CPU-based solvers (e.g., KaMIS) on Maximum Independent Set problem.
result AI-inspired methods are often outperformed by classical CPU-based solvers, even with post-processing techniques.
Signatory calculates signature and logsignature transforms efficiently on CPU and GPU.
problem Efficient computation of signature and logsignature transforms for machine learning.
method CPU and GPU parallelism, backpropagation, efficient precomputation strategies, algorithmic improvements.
result Substantial speedups on CPU and GPU, including real-world applications.
Benchmarking TPU, GPU, and CPU for deep learning models.
problem Improving performance in deep learning training.
method ParaDnn benchmark suite for FC, CNN, and RNN models on TPU, GPU, and CPU.
result TPU, GPU, and CPU have unique strengths for different types of models.
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.
We present Caffe con Troll (CcT), a fully compatible end-to-end version of the popular framework Caffe with rebuilt internals. We built CcT to examine the performance characteristics of training and deploying general-purpose convolutional neural networks across different hardware architectures. We find that, by employi…
Asymmetry PRISM outperforms CPU and GPU solvers for institutional rebalancing.
problem Institutional rebalancing with deadline constraints
method Asymmetry PRISM
result Asymmetry PRISM-CPU is 4.5x to 24.1x faster than the fastest completed reference row in the same lane.
As machine learning algorithms enter applications in industrial settings, there is increased interest in controlling their cpu-time during testing. The cpu-time consists of the running time of the algorithm and the extraction time of the features. The latter can vary drastically when the feature set is diverse. In this…
New suboptimal algorithm for best subset selection in high-dimensional data.
problem Nonconvex and computationally challenging best subset selection in linear regression.
method Introducing a new suboptimal algorithm and comparing it with other popular methods.
result The new procedure is a competitive suboptimal algorithm for high-dimensional data.
This study uses LSTM and SARIMA models to forecast CPU usage in cloud computing.
problem Predicting future CPU usage in cloud computing centers.
method Used LSTM and SARIMA models to forecast CPU usage over short and long time scales.
result SARIMA model performed better for long-term predictions but LSTM was more robust.
GraphVite efficiently trains node embeddings for large networks.
problem Scaling node embedding algorithms to handle large networks (tens of millions of nodes).
method CPU-GPU hybrid system with parallel edge sampling and negative sampling.
result GraphVite achieves high performance (50x faster) for large networks.
pySigLib speeds up signature-based computations on CPUs and GPUs.
problem Efficient signature-based computations on large datasets and long sequences.
method Optimised Python library for CPU and GPU, novel differentiation scheme.
result Accurate gradients at a fraction of the runtime of existing libraries.
Framework optimizes cloud container sizing for ML tasks.
problem Challenges in cloud container configuration for ML services.
method Autonomous scaling using nested-loop Monte Carlo simulation.
result Reduces compute cost and accelerates ML algorithms.
RFX accelerates and compresses Random Forests for large datasets.
problem Memory bottleneck in proximity matrices limits Random Forest analysis.
method QLORA compression, CPU TriBlock storage, GPU batch sizing, 3D MDS visualization.
result Proximity-based Random Forest analysis on larger datasets is feasible.
The graphics processing unit (GPU) has emerged as a powerful and cost effective processor for general performance computing. GPUs are capable of an order of magnitude more floating-point operations per second as compared to modern central processing units (CPUs), and thus provide a great deal of promise for computation…
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.
CatBoost boosts performance on datasets with categorical features.
problem Handling categorical features in gradient boosting.
method Gradient boosting library with GPU and CPU implementations.
result Outperforms existing implementations on popular datasets.
Automated framework optimizes DNN deployment on Arm CPUs.
problem Lack of globally optimised DNN deployment across software levels.
method Reinforcement Learning search for automated design space exploration.
result Up to 4x improvement in performance and 2x reduction in memory.
Python framework for distributed Keras training on multiple GPUs/CPU.
problem Efficiently training neural networks on multiple GPUs/CPU.
method Built on Keras, uses MPI for coordination, suitable for supercomputing.
result Demonstrated performance on various system sizes.
KineticSim accelerates financial market simulations 3406x over CPU.
problem Simulating financial markets at scale with multi-agent models is bottlenecked by sequential processing and GPU kernel overhead.
method Formalized and implemented a reusable parallel design pattern for iterative multi-agent reductions in thread-block shared memory.
result Achieved a peak throughput of over 54.7 billion agent-events per second, delivering 3406x speedup over CPU.
Kymatio simplifies scattering transforms for Python.
problem Signal processing and machine learning applications.
method Wavelet scattering transform implemented in Python.
result Efficient, GPU-accelerated implementation.
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…
Introduces BMF for efficient matrix factorization of large data.
problem Efficiently factorizing large scale matrices with limited memory.
method Uses block matrix approach and factorization at a block level.
result Demonstrates faster convergence on large matrices.
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.
A new method uses Legendre multiwavelets to price discrete double barrier options efficiently.
problem Pricing discrete double barrier options efficiently with reduced CPU time.
method Approximating recursive solutions of the heat equation using Legendre multiwavelets and operational matrix form.
result The method significantly reduces CPU time and is efficient for increasing monitoring dates.
Paper proposes a new loss function for PU learning without negative examples.
problem Traditional machine learning struggles with negative examples, leading to biased predictions.
method Developed a collective loss function (cPU) for positive and unlabeled data.
result The cPU consistently outperforms existing methods in PU learning benchmarks and real-world datasets.
ONLAD Core detects anomalies in edge devices with fast learning and low power.
problem Anomaly detection in edge devices with concept drift and data transfers.
method Highly optimized neural network-based anomaly detection on edge devices.
result ONLAD Core achieves fast anomaly detection and low power consumption.
Polylab is a MATLAB toolbox for multivariate polynomial modeling.
problem Efficiently modeling and manipulating multivariate polynomials across CPU and GPU.
method Unified symbolic-numeric interface, three aligned classes (MPOLY, MPOLY_GPU, MPOLY_HP), polynomial operations, differentiation, matrix computations.
result Advantages of MPOLY-HP for reduction-heavy simplification and large-scale computations, and the stochastic log-determinant variant for sparse regimes.
In this paper, we discuss software design issues related to the development of parallel computational intelligence algorithms on multi-core CPUs, using the new Java 8 functional programming features. In particular, we focus on probabilistic graphical models (PGMs) and present the parallelisation of a collection of algo…
High performance computing (HPC) is a very attractive and relatively new area of research, which gives promising results in many applications. In this paper HPC is used for pricing of American options. Although the American options are very significant in computational finance; their valuation is very challenging, espe…
A fast numerical method for pricing double barrier options using Lagrange interpolation.
problem Pricing discrete double barrier knock-out call options efficiently.
method Approximating recursive solutions of the heat equation with Lagrange interpolation on Jacobi polynomials nodes.
result The method significantly reduces CPU time as the number of monitoring dates increases.
Stochastic simulation techniques employed for the analysis of portfolios of insurance/reinsurance risk, often referred to as `Aggregate Risk Analysis', can benefit from exploiting state-of-the-art high-performance computing platforms. In this paper, parallel methods to speed-up aggregate risk analysis for supporting re…
A new method reduces the cost of solving large-scale linear models.
problem Solving large-scale linear statistical models efficiently.
method Sequential Preconditioned Conjugate Gradient Method (SPCG).
result SPCG achieves OLS prediction accuracy with fewer iterations and less time.
Improved RBM training speed using parallel computing.
problem High computational cost of training RBM models.
method Parallelized training using Horovod framework.
result Training time reduced to less than 12 minutes on 64 CPU nodes.
PL-NMF improves parallel NMF by optimizing data locality.
problem Data movement costs dominate in parallel NMF applications.
method Developed a parallel NMF algorithm based on HALS with data locality optimizations.
result Significant performance improvement over existing parallel NMF algorithms.
KineticSim: A lightweight, high-performance execution engine for real-time market simulators
problem Simulating financial markets at scale with multi-agent models
method Reusable parallel design pattern: persistent, state-carrying clearing for iterative multi-agent reductions
result Reduces per-step critical-path depth from Theta(L+A) to Theta(log L + ceil(A/L))
New method generates novel samples from closed-form diffusion models.
problem Closed-form SGMs memorize training data and cannot generate novel samples.
method Explicitly smooth closed-form score, use nearest-neighbor estimator.
result Efficient method generates novel samples without training.
The paper proposes a method to measure fairness through equality of effort using algorithmic recourse.
problem Measuring fairness through equality of effort in automated systems.
method Applying algorithmic recourse to quantify equality of effort, overcoming previous limitations.
result An algorithm for assessing equality of effort has been developed and validated.
CUDA optimized neural network predicts HbA1c from joint mobility and anthropometrics.
problem Early detection and accurate diagnosis of diabetes.
method Parallelized neural network using CUDA and C++ on Nvidia GPUs.
result Achieved high accuracy (95.65% on training, 86.67% on testing for males; 97.73% on training, 66.67% on testing for females).
New method to estimate doctors' effort in annotating medical images.
problem High effort and expense in annotating medical images.
method Proposes a new criterion to evaluate effort, uses active learning and U-shape network for annotation strategy, and fine annotation platform to reduce effort.
result State-of-the-art segmentation performance achieved with only 60% annotation candidates, reducing effort by 44-47%.
SySCD improves SCD scalability and speeds up training.
problem Scalability issues in parallel SCD algorithms.
method Developed a system-aware parallel SCD algorithm (SySCD) to avoid bottlenecks.
result Offers up to x42 speedup compared to state-of-the-art GLM solvers.
Models show strategic agents can influence classifier outcomes by investing effort.
problem How strategic agents can influence classifier outcomes.
method Developed a model to characterize strategic effort investment.
result Simple linear mechanisms can incentivize strategic effort effectively.