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.
Tensor trains speed up option pricing for multi-asset options.
problem Speeding up option pricing for multi-asset options.
method Tensor train learning algorithms to compress functions with parameter dependence.
result The proposed method outperforms Monte Carlo-based pricing in computational complexity.
AdaScale SGD adapts learning rates for large-batch training efficiently.
problem Adapting learning rates for large-batch training to balance speed-ups and model quality.
method Adaptive learning rate adaptation based on gradient variance.
result AdaScale achieves reliable speed-ups for a wide range of batch sizes without degrading model quality.
New RL approach speeds up training across tasks.
problem Training reinforcement learning models quickly and efficiently.
method Combines planning quasi-metric and task-specific aimers.
result Achieves multiple-fold speed-up on bit-flip and robotic arm tasks.
Multirate training speeds up neural network fine-tuning.
problem Efficiently fine-tuning deep neural networks.
method Partitioning neural network parameters into fast and slow parts, updating slowly over longer intervals.
result Significant computational speed-up for transfer learning tasks.
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…
Quantum algorithms speed up reinforcement learning policies in large state-action spaces.
problem Limitations of quantum access in training reinforcement learning policies.
method Designing quantum algorithms to train reinforcement learning policies.
result Quantum algorithms offer full quadratic speed-ups in sample complexity for well-behaved policies.
Averaging recent model checkpoints speeds up training time.
problem Training large vision or language models is time-consuming.
method Average the weights of the k latest checkpoints.
result Speeds up training by dozens of epochs, saving up to 68 GPU hours.
New methods speed up training of differentially private deep learning models.
problem Training differentially private deep learning models is slower than non-private models.
method Derive and implement new per-example gradient clipping methods compatible with auto-differentiation.
result Significant training speed-ups (54x - 94x) for various models and architectures.
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.
A new interpolation method speeds up neural ODE training.
problem Efficiently approximating gradients in neural ODEs.
method Interpolation-based technique to approximate gradients.
result Our method trains neural ODEs faster than the reverse dynamic method.
FedSARSA converges with heterogeneous agents, achieving linear speed-up.
problem Convergence analysis of Federated SARSA with heterogeneous agents.
method Linear function approximation, local training, multi-step error expansion.
result FedSARSA achieves linear speed-up with respect to the number of agents.
sGBM speeds up gradient boosting by parallelizing and adapting base learners.
problem Infeasibility of parallelizing GBM training and sub-optimal performance in online settings.
method Integrates multiple differentiable base learners, jointly optimizing them with linear speed-up.
result sGBM achieves higher time efficiency and better accuracy than traditional GBM.
New method speeds up training of large kernel models.
problem Scaling kernel machines to large datasets and model sizes.
method Delayed projections in Preconditioned Stochastic Gradient Descent (PSGD).
result Significant training speed up over existing methods.
Hessian-free training has become a popular parallel second or- der optimization technique for Deep Neural Network training. This study aims at speeding up Hessian-free training, both by means of decreasing the amount of data used for training, as well as through reduction of the number of Krylov subspace solver iterati…
CodedFedL speeds up federated learning in MEC networks by 15x.
problem Slow convergence in federated learning due to heterogeneity and stochastic fluctuations.
method Injects structured coding redundancy into federated learning to mitigate stragglers and speed up training.
result CodedFedL speeds up the training procedure by up to 15x compared to benchmark schemes.
Artificial Neural Networks (ANNs) have received increasing attention in recent years with applications that span a wide range of disciplines including vital domains such as medicine, network security and autonomous transportation. However, neural network architectures are becoming increasingly complex and with an incre…
Scale of data and scale of computation infrastructures together enable the current deep learning renaissance. However, training large-scale deep architectures demands both algorithmic improvement and careful system configuration. In this paper, we focus on employing the system approach to speed up large-scale training.…
Orthogonal initialization does not speed up training in ultra-wide neural networks.
problem Exploring the effect of orthogonal initialization on training speed in deep neural networks.
method Study of neural tangent kernel dynamics in FCNs and CNNs with orthogonal initialization.
result The NTK of orthogonally-initialized networks remains constant during training, suggesting no speedup in the NTK regime.
This dissertation shows that careful injection of noise into sample data can substantially speed up Expectation-Maximization algorithms. Expectation-Maximization algorithms are a class of iterative algorithms for extracting maximum likelihood estimates from corrupted or incomplete data. The convergence speed-up is an e…
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.
Proposes faster neural network learning by using subsets of training data.
problem Manual design and validation of network topologies is time-consuming.
method Exploits subsets of training data at each incremental training step and performs online hyperparameter selection.
result Significantly reduces overall training time while maintaining performance.
HPSGD speeds up DNN training by paralleling data sync with local training.
problem Low cluster utilization in distributed deep neural network training.
method Hierarchical Parallel SGD (HPSGD) with improved model updating for stale gradients.
result Significantly boosts distributed DNN training and reduces stale gradients.
Faster training of neural ODEs using Gauß-Legendre quadrature.
problem Training neural ODEs is slow due to solving ODEs numerically.
method Use Gauß-Legendre quadrature to solve integrals faster than ODE-based methods.
result Faster training of neural ODEs, especially for large models.
A scalable graphical method is presented for selecting, and partitioning datasets for the training phase of a classification task. For the heuristic, a clustering algorithm is required to get its computation cost in a reasonable proportion to the task itself. This step is proceeded by construction of an information gra…
A new method to rescale ReLU neural networks based on path-lifting.
problem Lack of principled ways to leverage rescaling symmetries in ReLU neural networks.
method Introduces a geometrically motivated criterion to rescale neural network parameters, aligning a kernel in the path-lifting space with a chosen reference.
result Proposed method can speed up training and aligns a kernel in the path-lifting space with a chosen reference.
Data-driven modeling increasingly requires to find a Nash equilibrium in multi-player games, e.g. when training GANs. In this paper, we analyse a new extra-gradient method for Nash equilibrium finding, that performs gradient extrapolations and updates on a random subset of players at each iteration. This approach prova…
ZORB speeds up neural network training without sacrificing accuracy.
problem Slow and strenuous training of neural networks using gradient descent.
method Uses pseudoinverse of targets instead of gradients for backpropagation.
result ZORB converges 300 times faster than Adam on MNIST without hyperparameter tuning.
APMSqueeze improves Adam for faster training with less communication.
problem Adam's inefficiency in parallel training due to gradient compression limitations.
method Error-compensated gradient compression for Adam-preconditioned Momentum SGD.
result Significantly reduces communication time per epoch without sacrificing accuracy.
GPU acceleration speeds up financial machine learning training time.
problem Time-intensive classifier training in financial machine learning.
method Deployed NVIDIA GPUs for parallel high-speed arithmetic operations.
result Significantly faster training time achieved.
Deep learning models can take weeks to train on a single GPU-equipped machine, necessitating scaling out DL training to a GPU-cluster. However, current distributed DL implementations can scale poorly due to substantial parameter synchronization over the network, because the high throughput of GPUs allows more data batc…
Training machine learning (ML) models on large datasets requires considerable computing power. To speed up training, it is typical to distribute training across several machines, often with specialized hardware like GPUs or TPUs. Managing a distributed training job is complex and requires dealing with resource contenti…
In this paper, we propose a speed-up approach for subclass discriminant analysis and formulate a novel efficient multi-view solution to it. The speed-up approach is developed based on graph embedding and spectral regression approaches that involve eigendecomposition of the corresponding Laplacian matrix and regression …
Gaussian process regression (GPR) is a non-parametric Bayesian technique for interpolating or fitting data. The main barrier to further uptake of this powerful tool rests in the computational costs associated with the matrices which arise when dealing with large data sets. Here, we derive some simple results which we h…
AlgoPerf competition evaluates neural network training speed-ups.
problem Improving neural network training speed using better algorithms.
method Compared 18 diverse submissions from 10 teams on multiple workloads.
result Schedule Free AdamW algorithm achieved best results in self-tuning ruleset.
Quantum computing speeds up neural network training and retraining.
problem Inefficient classical training and retraining of neural networks.
method Adiabatic quantum computing to optimize Kolmogorov-Arnold Networks using Bezier curves.
result Quantum optimization achieves 100x faster retraining compared to classical methods.
In this paper, we propose the nonlinearity generation method to speed up and stabilize the training of deep convolutional neural networks. The proposed method modifies a family of activation functions as nonlinearity generators (NGs). NGs make the activation functions linear symmetric for their inputs to lower model ca…
K-FAC speeds up training of modern neural networks with linear weight-sharing.
problem Efficiently training modern neural networks with linear weight-sharing layers.
method Kronecker-Factored Approximate Curvature (K-FAC) applied to linear weight-sharing layers.
result K-FAC-reduce is generally faster than K-FAC-expand for deep linear networks.
We propose a method to impose homogeneous linear inequality constraints of the form Ax≤0 on neural network activations. The proposed method allows a data-driven training approach to be combined with modeling prior knowledge about the task. One way to achieve this task is by means of a projection step at test time…
Speeds up deep neural networks training by 10x using GPU concurrency.
problem Training deep residual neural networks efficiently.
method Layer-wise parallel training with GPU concurrency and Nonlinear Multigrid.
result 10.2x speedup over traditional techniques.
HollowFlow speeds up likelihood evaluation for large-scale models.
problem Prohibitive scaling of sample likelihood computations in flow-based models.
method Introduces HollowFlow, a flow-based generative model using a NoBGNN with a block-diagonal Jacobian structure.
result Achieves up to O(n^2) speed-up in likelihood evaluation for large systems.
Paper proposes a method to speed up DNNs by quantizing Winograd/Toom-Cook convolutions.
problem Speeding up convolution computations in DNNs with reduced time consumption and improved accuracy.
method Application of base change technique for quantized Winograd-aware training model.
result 8-bit quantized network achieves nearly the same accuracy as direct quantized convolution with minimal additional operations.
The paper uses deep learning to speed up spatial and visual connectivity analysis.
problem Slow calculation of spatial and visual connectivity metrics.
method Investigates machine learning models and a pipeline for training them on spatial and visual connectivity analysis.
result Deep learning models significantly speed up the analysis process.
Quantum state preparation framework speeds up basket option pricing.
problem Limited practical benefit of quantum amplitude estimation due to state-preparation depth.
method Structure-aware tensor-train rank-based variational state preparation.
result State-preparation depth scaling replaced with linear scaling, maintaining low basket-pricing errors.
Coded Federated Learning speeds up training in edge computing networks.
problem Slow convergence in Federated Learning due to heterogeneity and stochastic fluctuations.
method Exploiting statistical properties of compute and communication delays, distributed kernel embedding, and random Fourier features.
result Significant performance gains for CodedFedL in distributed non-linear regression and classification problems.
SparseProp speeds up SNN simulations and training by four orders of magnitude.
problem Efficiently simulating and training large spiking neural networks.
method Event-based algorithm that reduces computational cost from O(N) to O(log(N)) per spike.
result Numerically exact simulations of large spiking networks and efficient training using backpropagation.
A new method computes Greeks for multi-asset options using tensor trains and Fourier transforms.
problem Efficient computation of Greeks for multi-asset options with high accuracy and low sample complexity.
method Tensor train (TT) representations of Fourier-based pricing functions, combined with numerical differentiation or analytical approaches.
result Significant speed-ups of up to 105imes over Monte Carlo simulations while maintaining comparable accuracy. This paper speeds up Gaussian process regression for autocorrelated data.
problem Temporal overfitting in Gaussian process models for autocorrelated data.
method Modifying existing Gaussian process approximations to handle blocked, de-correlated data.
result Proposed methods accelerate Gaussian process regression on autocorrelated data without sacrificing performance.