This work reduces computation cost for on-device CNN training.
problem High computation cost during on-device CNN training.
method Self-supervised instance filtering and error map pruning.
result Substantial computation saving without significant accuracy loss.
This paper uses QUBO to train machine learning models on quantum computers.
problem Efficiently training machine learning models on quantum computers.
method Formulated three machine learning models (linear regression, SVM, k-means) as QUBO problems.
result Formulations are more efficient or equivalent in time and space complexity to classical methods.
Local SGD outperforms conventional methods in LLM training.
problem Training large language models on distributed devices.
method Local SGD algorithm applied to distributed training.
result Local SGD achieves competitive results in LLM training.
Benefitting from large-scale training datasets and the complex training network, Convolutional Neural Networks (CNNs) are widely applied in various fields with high accuracy. However, the training process of CNNs is very time-consuming, where large amounts of training samples and iterative operations are required to ob…
Efficient echo state network with explicit memory performs well on benchmark tasks.
problem Training differentiable neural computers is difficult and time-consuming.
method Echo state network with an explicit memory.
result Echo state network can recognize all regular languages, including those contractive networks cannot.
SWAP uses large mini-batches to train DNNs faster with good generalization.
problem Training deep neural networks with small mini-batches is time-consuming.
method SWAP computes an approximate solution with large mini-batches and refines it by averaging weights of multiple parallel models.
result SWAP trains models as well as small-batch training but in significantly less time.
CoNNTrA trains DNNs with low-power, low-memory constraints.
problem Training deep neural networks on edge computing systems with low power and memory usage.
method Coordinate gradient descent-based approach for training DNNs with constrained learning parameters.
result CoNNTrA models use 32x less memory and have comparable errors to Backpropagation models.
Distributed training of deep nets is an important technique to address some of the present day computing challenges like memory consumption and computational demands. Classical distributed approaches, synchronous or asynchronous, are based on the parameter server architecture, i.e., worker nodes compute gradients which…
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.
The paper predicts loss scaling across different datasets and compute scales.
problem Predicting loss scaling across different datasets and compute scales.
method Derive shifted power law relationships between train and test losses.
result Shifted power law relationships hold for various datasets and tasks, improving prediction accuracy.
Paper explores fast adversarial training to improve robustness with less computation.
problem Efficiently defending against adversarial examples.
method Integrates simple self-attacks for faster training, focusing on overfitting recovery.
result Shows superior robust accuracy with reduced training time compared to strong adversarial training.
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.
Existing methods for reducing the computational burden of neural networks at run-time, such as parameter pruning or dynamic computational path selection, focus solely on improving computational efficiency during inference. On the other hand, in this work, we propose a novel method which reduces the memory footprint and…
HeteroFL trains diverse clients with varying capabilities efficiently.
problem Training models on clients with different computational and communication capacities.
method Proposes HeteroFL framework to adaptively distribute subnetworks based on client capabilities.
result Adaptive subnetwork distribution leads to efficient computation and communication.
Crowdsourced training of large neural networks with decentralized Mixture-of-Experts.
problem Expensive training of large neural networks limits research contributions.
method Learning@home: decentralized Mixture-of-Experts for large, poorly connected participants.
result Performance and reliability of Learning@home surpass conventional distributed training.
A new method reduces deep learning training costs by 92%.
problem High computational cost of backpropagation in deep neural networks.
method Dithered backprop with non-subtractive dither quantization.
result 92% sparsity with minimal accuracy loss.
Coded Federated Learning speeds up model convergence by preemptively computing on parity data.
problem Federated learning's convergence is slow on heterogeneous platforms due to stragglers.
method Develops CFL scheme where clients generate parity data and share it once, allowing the server to compute redundantly.
result CFL allows global model to converge nearly four times faster than uncoded federated learning.
Scaling laws for neural language models reveal optimal model size and compute allocation.
problem Understanding the optimal model size and compute allocation for neural language models.
method Empirical analysis of scaling laws for cross-entropy loss across model size, dataset size, and compute.
result Simple equations govern the dependence of overfitting and training speed on model/dataset size and model size, respectively.
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.
It is well-known that neural networks are computationally hard to train. On the other hand, in practice, modern day neural networks are trained efficiently using SGD and a variety of tricks that include different activation functions (e.g. ReLU), over-specification (i.e., train networks which are larger than needed), a…
Training of large-scale deep neural networks is often constrained by the available computational resources. We study the effect of limited precision data representation and computation on neural network training. Within the context of low-precision fixed-point computations, we observe the rounding scheme to play a cruc…
We explore the robustness of recurrent neural networks when the computations within the network are noisy. One of the motivations for looking into this problem is to reduce the high power cost of conventional computing of neural network operations through the use of analog neuromorphic circuits. Traditional GPU/CPU-cen…
New method optimizes privacy and compute trade-offs for deep learning.
problem Privacy and compute trade-offs in deep learning training.
method Decoupling privacy analysis and experimental behavior, using TAN and scaling laws for DP-SGD.
result Stronger privacy guarantees with significant reduction in computational budget.
The intrinsic error tolerance of neural network (NN) makes approximate computing a promising technique to improve the energy efficiency of NN inference. Conventional approximate computing focuses on balancing the efficiency-accuracy trade-off for existing pre-trained networks, which can lead to suboptimal solutions. In…
Unreduced PDs can perform similarly to reduced PDs in machine learning tasks.
problem Ignoring much of the information in persistence diagrams in machine learning pipelines.
method Developed methods to generate topological feature vectors from unreduced boundary matrices.
result Unreduced PDs can perform on par with, and sometimes outperform, fully-reduced PDs in machine learning tasks.
New method reduces adversarial training time by up to 2.5x with comparable accuracy.
problem High computational complexity of adversarial training for deep neural networks.
method Replacing initial adversarial training with natural training.
result Significant reduction in training time (up to 2.5x) without loss in accuracy.
Securely share encrypted data for machine learning training.
problem Securely sharing encrypted data for machine learning training without revealing the data.
method Rotation based method using flow model.
result Theoretical justification and demonstration of effectiveness in different scenarios.
Automated Budget Constrained Training optimizes model training under time constraints.
problem Balancing model quality and computational cost in constrained time.
method Developed a hyperparameter optimisation algorithm that learns the relationship between hyperparameters, model quality, and computational cost.
result The algorithm optimally decides whether to terminate or continue training, and what hyperparameters to use.
A fast method for LOOCV in k-NN regression reduces computation time.
problem Efficient computation of LOOCV for k-NN regression.
method Identical LOOCV estimate to (k+1)-NN MSE on training data.
result LOOCV computation can be done with (k+1)-NN regression once.
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.
The high computational complexity associated with training deep neural networks limits online and real-time training on edge devices. This paper proposed an end-to-end training and inference scheme that eliminates multiplications by approximate operations in the log-domain which has the potential to significantly reduc…
New method compresses LSTM networks using MPS tensor trains.
problem Challenges in maintaining performance of compressed RNNs.
method Use of MPS tensor trains for LSTM network compression.
result MPS tensor trains outperform MPOs in storage and inference time.
Support Vector Data Description (SVDD) is a popular outlier detection technique which constructs a flexible description of the input data. SVDD computation time is high for large training datasets which limits its use in big-data process-monitoring applications. We propose a new iterative sampling-based method for SVDD…
New insights into training ReLU networks, especially as data dimensionality increases.
problem Understanding computational complexity of training ReLU networks with varying data dimensions.
method Analyzed the parameterized complexity of two-layer ReLU networks with respect to various loss functions, focusing on the influence of data dimensionality.
result Running time lower bounds and optimal brute-force strategies for training ReLU networks, extending previous results to broader loss functions.
This paper proposes a new D2D data sharing approach to improve distributed machine learning training speed.
problem Straggler dilemma in distributed edge learning.
method Proposes a D2D data sharing approach to balance computation loads and optimize radio resource allocation.
result Significantly reduces training delay and enhances training accuracy in non-i.i.d. data environments.
This work simplifies Gaussian process regression for multiple outputs.
problem Exponential computational complexity in Gaussian process regression.
method Approximating the covariance kernel using eigenvalues and functions.
result Significant reduction in training and regression complexity.
Training state-of-the-art, deep neural networks is computationally expensive. One way to reduce the training time is to normalize the activities of the neurons. A recently introduced technique called batch normalization uses the distribution of the summed input to a neuron over a mini-batch of training cases to compute…
Pruning filters in neural networks improves performance and reduces costs.
problem Large neural networks have high inference costs and limited resource usage.
method Batch Bridgeout for efficient pruning of convolutional filters.
result Batch Bridgeout trained networks achieve higher accuracy across various pruning intensities.
Low-rank training improves neural network training on edge devices with non-volatile memory.
problem Training neural networks on edge devices with non-volatile memory, especially in terms of write density and auxiliary memory.
method Low-rank training scheme to address write density and auxiliary memory limitations.
result The low-rank training technique outperforms standard SGD in accuracy and weight writes.
Model predicts neural network performance scaling laws across various factors.
problem Understanding the performance of neural networks across different training factors.
method Random feature model trained with gradient descent, analyzing compute-optimal scaling laws.
result Predicts asymmetric compute-optimal scaling rule and behavior of training and test loss gap.
Efficiently computes per-example gradients in CNNs for differential privacy.
problem Computing per-example gradients in CNNs for differential privacy.
method Comparison of existing strategies and introduction of a new per-example gradient calculation method.
result The new method is advantageous depending on model architecture and training.
This work analyzes and optimizes memory and compute costs of learned optimizers.
problem High memory and compute costs of learned optimizers.
method Identified and quantified design features of learned and hand-designed optimizers, constructed a more efficient learned optimizer.
result A learned optimizer that is faster and more memory efficient than previous work.
Paper introduces a new method to compute pseudoinverse for ELM with large datasets.
problem Efficient computation of pseudoinverse for ELM with large datasets.
method Rank-based matrix decomposition of the hidden layer matrix.
result Optimal training time and reduced computational complexity for large hidden nodes.
NGRC shows numerical instabilities with short lags and high-degree polynomials.
problem Numerical instabilities in NGRC feature matrix.
method Combining numerical linear algebra and dynamical systems theory, we study feature matrix conditioning. We evaluate different numerical algorithms for solving the regularized least-squares problem.
result SVD-based training achieves accurate forecasts without regularization, preferable for short lags and high-degree polynomials.
New method for decentralized learning reduces data and computation needs.
problem High complexity and data/compute requirements for neural network training.
method Asynchronous updates over unreliable network using Distributed Averaging Consensus.
result Models can be learned on highly biased datasets with intermittent communication.
This study explores training Bayesian neural networks at scale using high-performance computing.
problem Challenges in training Bayesian neural networks at scale due to computational overhead.
method High-performance computing with distributed training, network pruning.
result Pruning up to 80% of the network can reduce inference time by 7.0% without significant accuracy loss.
The reservoir computing paradigm is employed to classify heartbeat anomalies online based on electrocardiogram signals. Inspired by the principles of information processing in the brain, reservoir computing provides a framework to design, train, and analyze recurrent neural networks (RNNs) for processing time-dependent…
This paper optimizes deep learning training by efficiently sharding weight updates across replicas.
problem Redundant weight update computation on all replicas in data-parallel training.
method Automatic sharding of weight updates using static analysis and transformations on the training graph.
result Substantial speedups achieved on large-scale models using Cloud TPUs.