Optimized parallel RNN training reaches up to 845x speedup.
problem Expensive RNN training through back-propagation through time (BPTT).
method Optimized parallel algorithm \opt based on ELM, leveraging GPU shared memory and QR factorization.
result Up to 845x speedup over sequential training and 20x less time to train.
A new algorithm speeds up deep learning training by decoupling computation and communication.
problem High communication cost limits the speedup of distributed SGD.
method CoCoD-SGD: runs computation and communication in parallel.
result Linear time speedup with respect to hardware resources.
GPU optimization speeds up large-scale classification tasks.
problem Efficiently training large-scale classification models on GPUs.
method Judecious GPU-optimization principles applied to TRON algorithm.
result Significant speedups for logistic regression and SVM classification.
Federated Q-Learning achieves linear regret speedup with low communication cost.
problem Achieving linear regret speedup in federated reinforcement learning without high communication costs.
method Proposed two federated Q-Learning algorithms: FedQ-Hoeffding and FedQ-Bernstein, using event-triggered synchronization, novel step size selection, and concentration inequalities.
result Total regrets achieve linear speedup compared to single-agent counterparts with logarithmic communication cost.
Linear speedup achieved in non-convex optimization for decentralized systems.
problem Achieving optimal performance in decentralized non-convex optimization.
method Examined the dependence of convergence guarantees on spectral properties of combination policies.
result Linear speedup in saddle-point escape time for symmetric combination policies.
A fast method for Lasso and Logistic Lasso problems.
problem Solving Lasso and Logistic Lasso regression problems efficiently.
method Iterative active set approach using solver updates.
result 31.41 times faster on average for compressed sensing.
Predicting structured outputs can be computationally onerous due to the combinatorially large output spaces. In this paper, we focus on reducing the prediction time of a trained black-box structured classifier without losing accuracy. To do so, we train a speedup classifier that learns to mimic a black-box classifier u…
Improved K-Means++ and K-Means∥ with faster run-time.
problem Efficiently selecting initial seeds for K-means clustering.
method Triangle inequality pruning and dynamic priority queue.
result Up to 17x speedup for K-Means++ and 551x for K-Means$\$.
Quantum algorithm speeds up nested expectation estimation by nearly quadratically.
problem Estimating repeatedly nested expectations with quantum computing.
method Proposes a quantum algorithm achieving nearly quadratic speedup over classical methods.
result Achieves nearly quadratic speedup for RNEs, up to logarithmic factors.
We parallelize backpropagation for deep learning models, achieving significant speedups.
problem Sequential dependency in backpropagation limits scalability on parallel systems.
method Reformulated backpropagation as a scan operation, using Blelloch scan algorithm.
result Up to 2.75x speedup on overall training time and 108x on backward pass.
DASA speeds up SA with delayed agents, achieving N-fold speedup.
problem Speeding up Stochastic Approximation with asynchronous delays.
method DASA: Delay-Adaptive Multi-Agent Stochastic Approximation algorithm.
result First algorithm with convergence rate dependent on mixing time and average delay.
ECD algorithm speeds up non-convex optimization, offering quantum and stochastic enhancements.
problem Non-convex optimization challenges in machine learning.
method Energy Conserving Descent (ECD) algorithm, stochastic ECD dynamics (sECD), quantum ECD Hamiltonian (qECD).
result ECD and its quantum version achieve exponential speedup over gradient descent.
GPU-optimized ES-RNN boosts time series forecasting speed by 322x.
problem Efficiently forecasting time series data.
method Vectorized GPU implementation of ES-RNN.
result Up to 322x speedup in training time.
The Graph Convolutional Network (GCN) model and its variants are powerful graph embedding tools for facilitating classification and clustering on graphs. However, a major challenge is to reduce the complexity of layered GCNs and make them parallelizable and scalable on very large graphs -- state-of the art techniques a…
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…
Paper speeds up large foundation models for time series data.
problem Resource-intensive foundation models limit accessibility.
method Dimensionality reduction techniques, including PCA and neural network adapters.
result Up to 10x speedup and 4.5x more datasets fit on a single GPU.
Quantum algorithm speeds up portfolio optimization.
problem Optimizing portfolios with constraints.
method Developed a quantum algorithm with running time complexity.
result Quantum algorithm can achieve polynomial speedup over classical algorithms.
Chemical transport models (CTMs), which simulate air pollution transport, transformation, and removal, are computationally expensive, largely because of the computational intensity of the chemical mechanisms: systems of coupled differential equations representing atmospheric chemistry. Here we investigate the potential…
Paper analyzes convergence and speedup of asynchronous parallel SGD.
problem Achieving good convergence and linear speedup in asynchronous parallel SGD.
method Second-order convergence analysis of APSGD with consistent read near strictly saddle points.
result Theoretical guarantee for using at most O(K1/3M−1/3) workers for good convergence and linear speedup. Best arm identification (or, pure exploration) in multi-armed bandits is a fundamental problem in machine learning. In this paper we study the distributed version of this problem where we have multiple agents, and they want to learn the best arm collaboratively. We want to quantify the power of collaboration under limi…
ProxSkip achieves linear speedup in distributed non-convex optimization.
problem Achieving linear speedup in distributed non-convex optimization.
method Unified convergence analysis for stochastic non-convex, convex, and strongly convex problems.
result ProxSkip achieves linear speedup in the number of nodes under stochastic gradients.
SliceOut speeds up deep learning training without sacrificing accuracy.
problem Frequent model re-training and large model training workloads in deep learning.
method SliceOut uses dropout-inspired scheme to drop contiguous sets of units at random, leveraging GPU memory layout.
result 10-40% speedups and memory reduction with minimal accuracy loss.
Neural networks offer high-accuracy solutions to a range of problems, but are costly to run in production systems because of computational and memory requirements during a forward pass. Given a trained network, we propose a techique called Deep Learning Approximation to build a faster network in a tiny fraction of the …
Quantum computing promises faster finance algorithms.
problem Solving finance problems faster than classical methods.
method Quantum computing applications to finance, including Monte Carlo, portfolio optimization, and machine learning.
result Quantum speedups for finance problems, especially Monte Carlo and portfolio optimization.
RNN operators solve Newton's equations with large timesteps for molecular dynamics.
problem Solving Newton's equations of motion with large timesteps for molecular dynamics simulations.
method Recurrent Neural Networks (RNN) operators to solve Newton's equations using past trajectory data.
result Significant speedup in molecular dynamics simulations with timesteps up to 4000 times larger.
New insights explain speedup saturation in distributed learning with large batches and delays.
problem Understanding and optimizing speedup in distributed learning with large batches and delays.
method Theoretical analysis of strongly convex, convex, and non-convex settings, considering data sparsity.
result Identification of a data-dependent parameter explaining speedup saturation in both batch size and gradient staleness.
Quantum computing offers a quadratic speedup for estimating non-linear functionals.
problem Estimating non-linear functionals of probability distributions.
method Proposes a quantum-inside-quantum Monte Carlo algorithm for a broad class of non-linear estimation problems.
result Achieves a quadratic speedup for non-linear estimation problems, including nested conditional expectations and stochastic optimization.
This work optimizes deep learning training by combining data and model parallelism.
problem Training large models with multiple GPUs suffers from high communication overhead and statistical efficiency loss.
method Hybrid parallelization combining data and model parallelism.
result Hybrid training provides significant speedup compared to data parallelism alone.
Efficient algorithm finds fast Transformer models.
problem Slow inference time of Transformer models.
method Decompose Transformer architecture into components, use sampling-based one-shot search.
result Achieved 10% to 30% speedup on pre-trained BERT and 70% on top of a previous state-of-the-art model.
Sparse representations using data dictionaries provide an efficient model particularly for signals that do not enjoy alternate analytic sparsifying transformations. However, solving inverse problems with sparsifying dictionaries can be computationally expensive, especially when the dictionary under consideration has a …
A new multilevel framework speeds up ResNet training.
problem Training deep residual networks (ResNets) is time-consuming.
method Formulates ResNets as dynamical systems and uses time-dependent optimal control problems.
result Enhanced training of ResNets with multilevel auxiliary networks achieves significant speedup.
MACER accelerates error repair by modularly identifying and applying fixes.
problem Automated compilation error repair for novice programmers.
method Modular segregation of repair process into identification and application, using discriminative learning techniques.
result MACER outperforms existing methods by 20% on popular errors and is competitive on all error types.
Optimized parallel algorithms for identifying strong ties in data.
problem Identifying strong ties in data with varying distances and community sizes.
method Design and analysis of sequential and parallel algorithms for partitioned local depths.
result Optimized algorithms achieve up to 19.4x speedup in parallel execution.
COPML framework securely trains models across multiple data owners without revealing individual data.
problem Privacy-preserving collaborative machine learning with multiple data owners.
method Securely encodes data, distributes computation, performs distributed training.
result Achieves up to 16x speedup in training time while maintaining strong privacy.
New algorithm achieves linear speedup in non-i.i.d. federated bilevel learning.
problem Linear speedup in convergence for non-i.i.d. datasets in federated bilevel optimization.
method Proposes FedMBO with a novel client sampling scheme for non-i.i.d. datasets.
result Achieves a convergence rate of O(1/√(nK) + 1/K + √n/K³/²).
SDM Policy accelerates inference for robotic tasks while maintaining high action quality.
problem Prolonged inference times in diffusion-based policies for high-frequency control tasks.
method Two-stage optimization: score matching and distribution matching; dual-teacher mechanism.
result 6x inference speedup with state-of-the-art action quality.
PowerSGD compresses gradients for faster distributed optimization.
problem Communication bottleneck in data-parallel distributed optimization.
method Low-rank gradient compressor based on power iteration.
result Achieves test performance on par with SGD and consistent speedups.
System learns optimizer hyperparameters to generalize across tasks.
problem Lack of generalization in learning optimizers for neural networks.
method Generalization-first approach, learning optimizer hyperparameters.
result System outperforms Adam on various tasks, including unseen modalities.
The impact of the maximally possible batch size (for the better runtime) on performance of graphic processing units (GPU) and tensor processing units (TPU) during training and inference phases is investigated. The numerous runs of the selected deep neural network (DNN) were performed on the standard MNIST and Fashion-M…
CSM-NN uses neural networks to speed up and improve the accuracy of logic circuit simulations.
problem Inaccurate and slow simulation of complex circuits with billions of transistors.
method Current Source Model (CSM) combined with optimized neural network structures and parallel processing.
result Reduces simulation time by up to 6x on CPUs and 15x on GPUs with less than 2% error.
Paper finds sharpness differences in transformer blocks accelerating LLM training.
problem Understanding and accelerating large language model pre-training.
method Uncovering sharpness disparity across transformer blocks and proposing Blockwise Learning Rate.
result Blockwise Learning Rate strategy accelerates LLM pre-training with lower loss and speedup.
Quantum algorithms speed up derivative pricing beyond Black-Scholes models.
problem Quantum speedups for derivative pricing beyond Black-Scholes models.
method Utilizing fast-forwardability and quantum Milstein sampler for non-GBM models, and improved numerical integration for GBM and CIR models.
result Quadratic speedups for derivative pricing in practical models like CIR and Heston's model.
Efficient medoid-based Silhouette method speeds up clustering evaluation.
problem Difficulty in evaluating clustering results due to many measures and data set dependence.
method Direct optimization of medoid-based Silhouette, combining PAM algorithm improvements.
result 10464x speedup in clustering evaluation for large datasets.
FROCC uses random projections for fast one-class classification.
problem Efficient one-class classification for large datasets.
method Random projection of data onto random unit vectors, with region bounding.
result Significant improvement in ROC performance with substantial speedup.
Unified analysis of Federated Averaging and Nesterov FedAvg for linear speedup.
problem Understanding convergence of FL algorithms under non-i.i.d. data and partial participation.
method Systematic study of convergence guarantees for FedAvg and Nesterov FedAvg under different conditions.
result Unified analysis of linear speedup for FedAvg and Nesterov FedAvg in various settings.
Quantum computing speeds up linear regression training.
problem Reducing training time for machine learning models.
method Formulated regression problem as QUBO, used D-Wave 2000Q for adiabatic optimization.
result Quantum approach achieves up to 2.8x speedup on larger datasets.
CHEETAH speeds up secure MLaaS by 100x over fastest existing schemes.
problem Privacy-preserving machine learning on end devices.
method Ultra-fast secure MLaaS framework using secret sharing.
result More than 100x speedup over fastest existing schemes.
Training deep networks is expensive and time-consuming with the training period increasing with data size and growth in model parameters. In this paper, we provide a framework for distributed training of deep networks over a cluster of CPUs in Apache Spark. The framework implements both Data Parallelism and Model Paral…