A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
A new scaling law predicts optimal batch size for training models.
ABS dynamically adjusts batch size based on policy stability, improving RL performance.
Large-batch training approaches have enabled researchers to utilize large-scale distributed processing and greatly accelerate deep-neural net (DNN) training. For example, by scaling the batch size from 256 to 32K, researchers have been able to reduce the training time of ResNet50 on ImageNet from 29 hours to 2.2 minute…
New analysis reveals batch size effects on stochastic conditional gradient methods.
Large-batch SGD is important for scaling training of deep neural networks. However, without fine-tuning hyperparameter schedules, the generalization of the model may be hampered. We propose to use batch augmentation: replicating instances of samples within the same batch with different data augmentations. Batch augment…
This work provides a scaling rule for model EMA optimization across batch sizes.
New framework optimizes deep learning training by deferring large batch sizes to late stages.
We determine the critical batch size for large language models and find it scales with data size, not model size.
Training deep neural networks using a large batch size has shown promising results and benefits many real-world applications. However, the optimizer converges slowly at early epochs and there is a gap between large-batch deep learning optimization heuristics and theoretical underpinnings. In this paper, we propose a no…
A new framework scales active search for large datasets.
AdaScale SGD adapts learning rates for large-batch training efficiently.
We investigate how the final parameters found by stochastic gradient descent are influenced by over-parameterization. We generate families of models by increasing the number of channels in a base network, and then perform a large hyper-parameter search to study how the test error depends on learning rate, batch size, a…
AdAdaGrad optimizes batch sizes for deep learning models, reducing the generalization gap.
Adam optimizer's bias is influenced by mini-batch size and momentum hyperparameters.
The paper improves Gaussian process models for efficient batch optimization.
Large-scale distributed training of deep neural networks suffer from the generalization gap caused by the increase in the effective mini-batch size. Previous approaches try to solve this problem by varying the learning rate and batch size over epochs and layers, or some ad hoc modification of the batch normalization. W…
Large-scale distributed training of deep neural networks results in models with worse generalization performance as a result of the increase in the effective mini-batch size. Previous approaches attempt to address this problem by varying the learning rate and batch size over epochs and layers, or ad hoc modifications o…
This paper explores the limits of large batch sizes in deep learning.
Leveraging the wealth of unlabeled data produced in recent years provides great potential for improving supervised models. When the cost of acquiring labels is high, probabilistic active learning methods can be used to greedily select the most informative data points to be labeled. However, for many large-scale problem…
New insights into learning rates and batch sizes for neural networks using random matrix theory.
In an increasing number of domains it has been demonstrated that deep learning models can be trained using relatively large batch sizes without sacrificing data efficiency. However the limits of this massive data parallelism seem to differ from domain to domain, ranging from batches of tens of thousands in ImageNet to …
Batch Normalization (BN) is capable of accelerating the training of deep models by centering and scaling activations within mini-batches. In this work, we propose Decorrelated Batch Normalization (DBN), which not just centers and scales activations but whitens them. We explore multiple whitening techniques, and find th…
Online method learns sparse models efficiently in large scale settings.
For large scale on-line inference problems the update strategy is critical for performance. We derive an adaptive scan Gibbs sampler that optimizes the update frequency by selecting an optimum mini-batch size. We demonstrate performance of our adaptive batch-size Gibbs sampler by comparing it against the collapsed Gibb…
BatchGFN uses generative flow networks for efficient batch active learning.
Pipelined Backpropagation trains large models without batches efficiently.
Recent work has shown how to train Convolutional Neural Networks (CNNs) rapidly on large image datasets, then transfer the knowledge gained from these models to a variety of tasks. Following [Radford 2017], in this work, we demonstrate similar scalability and transfer for Recurrent Neural Networks (RNNs) for Natural La…
Modern machine learning models are typically trained using Stochastic Gradient Descent (SGD) on massively parallel computing resources such as GPUs. Increasing mini-batch size is a simple and direct way to utilize the parallel computing capacity. For small batch an increase in batch size results in the proportional red…
The most straightforward method to accelerate Stochastic Gradient Descent (SGD) computation is to distribute the randomly selected batch of inputs over multiple processors. To keep the distributed processors fully utilized requires commensurately growing the batch size. However, large batch training often leads to poor…
In designing personalized ranking algorithms, it is desirable to encourage a high precision at the top of the ranked list. Existing methods either seek a smooth convex surrogate for a non-smooth ranking metric or directly modify updating procedures to encourage top accuracy. In this work we point out that these methods…
It is common practice to decay the learning rate. Here we show one can usually obtain the same learning curve on both training and test sets by instead increasing the batch size during training. This procedure is successful for stochastic gradient descent (SGD), SGD with momentum, Nesterov momentum, and Adam. It reache…
We propose a new learning to rank algorithm, named Weighted Margin-Rank Batch loss (WMRB), to extend the popular Weighted Approximate-Rank Pairwise loss (WARP). WMRB uses a new rank estimator and an efficient batch training algorithm. The approach allows more accurate item rank approximation and explicit utilization of…
Analysis of SGD+M convergence rates in high dimensions with batch size considerations.
A key component of most neural network architectures is the use of normalization layers, such as Batch Normalization. Despite its common use and large utility in optimizing deep architectures, it has been challenging both to generically improve upon Batch Normalization and to understand the circumstances that lend them…
Mini-batch stochastic gradient descent and variants thereof have become standard for large-scale empirical risk minimization like the training of neural networks. These methods are usually used with a constant batch size chosen by simple empirical inspection. The batch size significantly influences the behavior of the …
Increasing the batch size is a popular way to speed up neural network training, but beyond some critical batch size, larger batch sizes yield diminishing returns. In this work, we study how the critical batch size changes based on properties of the optimization algorithm, including acceleration and preconditioning, thr…
A new batch ensemble method reduces regret in stochastic bandits.
In statistical learning for real-world large-scale data problems, one must often resort to "streaming" algorithms which operate sequentially on small batches of data. In this work, we present an analysis of the information-theoretic limits of mini-batch inference in the context of generalized linear models and low-rank…
New method trains deep ResNets without normalization, achieving state-of-the-art performance.
Proposes m-POT to improve m-OT's misspecified mappings issue.
Seesaw optimizes training by balancing learning rate and batch size, accelerating model pretraining.
Federated learning for Bayesian clustering of large datasets.
Modern deep neural network training is typically based on mini-batch stochastic gradient optimization. While the use of large mini-batches increases the available computational parallelism, small batch training has been shown to provide improved generalization performance and allows a significantly smaller memory footp…
The paper refines and extends batched kernelized bandits, improving regret bounds and introducing a robust setting.
Study shows how mini-batch GD with random reshuffling affects least squares regression dynamics.
A new method improves active learning for large batch sizes.
New streaming methods improve convergence rates for optimization problems.
New algorithm tackles batched stochastic linear bandits with 1-bit communication constraints.