Predict training time without training using a linearized model.
problem Predicting the training time of a deep network without actual training.
method Approximate training dynamics with a linearized model and solve a low-dimensional SDE in function space.
result Predict training time within 20% error margin and 30-45x reduction in cost.
Neural network pruning with suitable retraining can yield networks with considerably fewer parameters than the original with comparable degrees of accuracy. Typical pruning methods require large, fully trained networks as a starting point from which they perform a time-intensive iterative pruning and retraining procedu…
Generative model uses random convolutional features to create financial time series.
problem Generating realistic financial time series with limited data and avoiding overfitting.
method Train generators by matching random convolutional features of real and generated time series, using SOCK (SOft Competing Kernels) feature map.
result Generators trained with random SOCK features outperform baselines across various financial datasets.
Delphyne improves financial time series models with pre-trained language models.
problem Lack of financial data and negative transfer effect in existing time-series pre-trained models.
method Delphyne is a pre-trained model for financial time series that addresses the lack of financial data and negative transfer effect.
result Delphyne achieves competitive performance and superior performances on various financial tasks.
The paper analyzes a neural network two-sample test using kernel analysis.
problem Determining if two datasets come from the same distribution.
method Time-analysis on a neural tangent kernel (NTK) two-sample test, extending to realistic neural network dynamics.
result Training times needed to detect deviations are well-separated in null and alternative hypothesis scenarios.
Gradient amplification boosts deep learning model performance without increasing training time.
problem Vanishing gradients in deep neural networks.
method Gradient amplification approach to prevent vanishing gradients and training strategy to enable/disable across epochs.
result Improves performance of deep learning models with reduced training time.
Recurrent neural networks (RNN) have been successfully applied to various sequential decision-making tasks, natural language processing applications, and time-series predictions. Such networks are usually trained through back-propagation through time (BPTT) which is prohibitively expensive, especially when the length o…
Paper develops large time series models using pre-trained transformers.
problem Performance bottlenecks in small models on data-scarce scenarios.
method Large-scale pre-training, unified time series format, GPT-style architecture.
result Generative pre-trained Time Series Transformer (Timer) for diverse tasks.
New method uses randomized sparse neural networks to solve time-dependent PDEs more accurately and efficiently.
problem Numerical challenges in training neural networks sequentially in time to solve time-dependent PDEs.
method Introduces Neural Galerkin schemes that update randomized sparse subsets of network parameters at each time step.
result Up to two orders of magnitude more accurate and two orders of magnitude faster than dense update schemes.
RDIS fills missing values in time series data explicitly.
problem Missing values in time series data.
method Random Drop Imputation with Self-training.
result RDIS achieves competitive results on real-world datasets.
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 measure assesses time series pre-training data quality without labels.
problem Challenges in collecting diverse pre-training datasets for time series classification.
method Contrastive-learning-based foundation model and contrastive accuracy measure.
result Contrastive accuracy correlates with model performance on downstream tasks.
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 is rapidly becoming a go-to tool for many artificial intelligence problems due to its ability to outperform other approaches and even humans at many problems. Despite its popularity we are still unable to accurately predict the time it will take to train a deep learning network to solve a given problem. T…
In this paper we propose a data augmentation method for time series with irregular sampling, Time-Conditional Generative Adversarial Network (T-CGAN). Our approach is based on Conditional Generative Adversarial Networks (CGAN), where the generative step is implemented by a deconvolutional NN and the discriminative step…
A hybrid training method reduces SNN training time and complexity.
problem Training deep SNNs is computationally expensive and time-consuming.
method Hybrid training technique combining initialization from converted SNNs and incremental spike-timing dependent backpropagation (STDB).
result The method converges in less than 20 epochs, reducing training complexity and time.
Enhances deep learning models for anomaly detection in time series data.
problem Anomalies in time series data corrupt performance of models.
method Monte Carlo EM for inferring anomaly indicators during training.
result Improves model performance on nominal data and anomalous points.
Neural network training process takes long time when the size of training data is huge, without the large set of training values the neural network is unable to learn features. This dilemma between time and size of data is often solved using fast GPUs, but we present a better solution for a subset of those problems. To…
This paper compares two methods for training neural ODEs in time-series regression and CNFs.
problem Training neural ODEs for time-series regression and CNFs efficiently.
method Discretize-Optimize (Disc-Opt) vs. Optimize-Discretize (Opt-Disc) approaches.
result Disc-Opt methods can achieve similar performance as Opt-Disc at inference with drastically reduced training costs.
Dynamic Influence Tracker measures changing sample importance during model training.
problem Static influence measurements during training overlook how sample importance varies over time.
method Dynamic Influence Tracker (DIT) captures time-varying sample influence across arbitrary time windows.
result DIT reveals distinct learning phases with shifting priorities and detects corrupted samples more efficiently.
Paper develops an efficient approach to reduce HPO time.
problem Challenges in determining optimal hyperparameters due to large number and training time.
method Nested Latin hypercube design for initialization, truncated additive Gaussian process model for calibration, sequential model-based algorithm for optimization.
result Demonstrates competitive performance on various machine learning 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…
This research improves financial market predictions using LSTM networks.
problem Accurate real-time forecasting of financial time series.
method Sequentially trained many-to-one LSTMs with adaptive training epochs.
result Our approach maintains superior accuracy as predictions are made further in the future.
Study improves sampling efficiency of diffusion models using RL and PDEs.
problem Training neural stochastic differential equations without access to target samples.
method Proves equivalences between RL methods and PDEs, uses coarse time discretization.
result Improves sample efficiency and reduces computational cost.
FPGA-based multi-layer equalizer adapts to changing channels.
problem Real-time adaptation to time-varying channel impairments.
method Multi-layer machine learning on FPGA with on-chip gradient backpropagation training.
result Real-time adaptation to changing channel conditions achieved.
This paper proposes reusing CNN layers to speed up hyperparameters tuning.
problem Time-consuming hyperparameters tuning in CNNs.
method Reuse trained convolutional layers among different trainings.
result Reduces training time and increases accuracy of neural networks.
Discrete random variables are natural components of probabilistic clustering models. A number of VAE variants with discrete latent variables have been developed. Training such methods requires marginalizing over the discrete latent variables, causing training time complexity to be linear in the number clusters. By appl…
Few-shot learning improves time-series forecasting with limited data.
problem Limited data in target tasks degrade forecasting performance.
method A few-shot learning method using recurrent neural networks with attention.
result The model forecasts future values effectively with minimal data.
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.
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.
Current state-of-the-art NMT systems use large neural networks that are not only slow to train, but also often require many heuristics and optimization tricks, such as specialized learning rate schedules and large batch sizes. This is undesirable as it requires extensive hyperparameter tuning. In this paper, we propose…
Improved continuous-time consistency models for large-scale image generation.
problem Training instability and discretization errors in existing diffusion models.
method Unified theoretical framework, improved diffusion process, and network architecture.
result Trained continuous-time CMs at 1.5B parameters, achieving state-of-the-art FID scores.
Deep learning has led to tremendous advancements in the field of Artificial Intelligence. One caveat however is the substantial amount of compute needed to train these deep learning models. Training a benchmark dataset like ImageNet on a single machine with a modern GPU can take upto a week, distributing training on mu…
Bayesian framework predicts post-disruption travel times in metro networks.
problem Uncertainty in post-disruption travel times in metro networks.
method Bayesian spatiotemporal modeling framework capturing train interactions and non-Gaussian distributional characteristics.
result The proposed models consistently outperform baseline specifications in point prediction and uncertainty quantification.
New DP training ensures models behave similarly at training and test time.
problem Standard SGD training leads to inconsistent model behavior at training and test time.
method Differentially-Private (DP) training ensures WYSIWYG property through distributional generalization.
result DP training guarantees high-level WYSIWYG property, improving model robustness and privacy.
Post-training corrections boost time-series forecasting accuracy.
problem Improving forecasting accuracy of large models after training.
method Sequential application of carefully selected corrections to predictions.
result Up to 30% improvement in forecasting accuracy with minimal overhead.
RNE provides a flexible framework for diffusion models, enabling inference-time control and energy-based training.
problem Insufficient knowledge of marginal densities in diffusion models.
method Introduces Radon-Nikodym Estimator (RNE) to reveal the connection between marginal densities and transition kernels.
result RNE delivers strong results in inference-time control and energy-based diffusion training.
SRNNs achieve LSTMs' online regression performance in less time.
problem Training LSTMs is time-consuming.
method First-order training algorithm with linear time complexity.
result SRNNs provide similar regression performance as LSTMs in shorter training time.
Gradient-flow optimization is reinterpreted as a statistical inference problem.
problem Optimizing training duration and assessing model performance in deep learning.
method Develops a statistical framework for gradient-flow training, treating it as a random-effects model.
result Establishes asymptotic optimality for prediction and reduces reliance on validation splits.
Model proposes neural network for continuous time dynamics with inductive biases.
problem Training neural networks for small datasets with nonlinear dynamics.
method Inductive biases on decay rates and frequencies using Koopman operator theory.
result Higher forecasting performance with single short training sequence.
uTSGAN improves on TSGAN for generating time series data.
problem Challenges in generating time-dependent data.
method Unified training of independent networks in TSGAN.
result uTSGAN outperforms TSGAN in 80% of benchmark datasets.
New method optimizes language model performance for test-time strategies.
problem Mismatch between training objectives and test-time deployment of large language models.
method Tail-Extrapolated estimators to approximate best-of-N performance from limited training rollouts.
result Improved performance of best-of-N deployment across various models and datasets.
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…
This paper develops a method to train compact neural networks with reduced memory and computational costs.
problem Training large neural networks consumes excessive resources and energy.
method End-to-end training framework using Bayesian tensor decomposition with automatic rank determination.
result The method achieves significant parameter reduction and maintains or improves accuracy.
Kernelized Support Vector Machines (SVMs) are among the best performing supervised learning methods. But for optimal predictive performance, time-consuming parameter tuning is crucial, which impedes application. To tackle this problem, the classic model selection procedure based on grid-search and cross-validation was …
Time series forecasting with limited data is a challenging yet critical task. While transformers have achieved outstanding performances in time series forecasting, they often require many training samples due to the large number of trainable parameters. In this paper, we propose a training technique for transformers th…
A simple GI loss improves temporal generalization without complex methods.
problem Temporal drift between train and test distributions in evolving data.
method Gradient Interpolation (GI) loss to regularize temporal complexity.
result GI loss outperforms complex methods on real-world datasets.
Self-guiding diffusion models improve time series forecasting, refinement, and generation.
problem Improving time series forecasting, refinement, and generation.
method Unconditionally-trained diffusion model with self-guidance mechanism.
result TSDiff outperforms task-specific conditional forecasting methods and maintains generative performance.