English
Related papers

Related papers: Dynamic Batch Adaptation

200 papers

While traditional Deep Learning (DL) optimization methods treat all training samples equally, Distributionally Robust Optimization (DRO) adaptively assigns importance weights to different samples. However, a significant gap exists between…

Despite the development of numerous adaptive optimizers, tuning the learning rate of stochastic gradient methods remains a major roadblock to obtaining good practical performance in machine learning. Rather than changing the learning rate…

Machine Learning · Statistics 2019-09-27 Hunter Lang , Pengchuan Zhang , Lin Xiao

Adam-type optimizers, as a class of adaptive moment estimation methods with the exponential moving average scheme, have been successfully used in many applications of deep learning. Such methods are appealing due to the capability on…

Machine Learning · Computer Science 2020-12-17 Bingxin Zhou , Xuebin Zheng , Junbin Gao

Adaptive optimizers, such as Adam, have achieved remarkable success in deep learning. A key component of these optimizers is the so-called preconditioning matrix, providing enhanced gradient information and regulating the step size of each…

Machine Learning · Computer Science 2024-12-10 Yun Yue , Zhiling Ye , Jiadi Jiang , Yongchao Liu , Ke Zhang

Self-paced learning and hard example mining re-weight training instances to improve learning accuracy. This paper presents two improved alternatives based on lightweight estimates of sample uncertainty in stochastic gradient descent (SGD):…

Machine Learning · Statistics 2018-01-09 Haw-Shiuan Chang , Erik Learned-Miller , Andrew McCallum

In order to extract the best possible performance from asynchronous stochastic gradient descent one must increase the mini-batch size and scale the learning rate accordingly. In order to achieve further speedup we introduce a technique that…

Computation and Language · Computer Science 2018-09-17 Nikolay Bogoychev , Marcin Junczys-Dowmunt , Kenneth Heafield , Alham Fikri Aji

Large language models (LLMs) have shown remarkable reasoning capabilities, yet aligning such abilities to small language models (SLMs) remains a challenge due to distributional mismatches and limited model capacity. Existing reasoning…

Computation and Language · Computer Science 2025-05-28 Yong Wu , Weihang Pan , Ke Li , Chen Binhui , Ping Li , Binbin Lin

We propose a Dynamic Scale Training paradigm (abbreviated as DST) to mitigate scale variation challenge in object detection. Previous strategies like image pyramid, multi-scale training, and their variants are aiming at preparing…

Computer Vision and Pattern Recognition · Computer Science 2021-03-16 Yukang Chen , Peizhen Zhang , Zeming Li , Yanwei Li , Xiangyu Zhang , Lu Qi , Jian Sun , Jiaya Jia

In recent years, large pre-trained Transformer-based language models have led to dramatic improvements in many natural language understanding tasks. To train these models with increasing sizes, many neural network practitioners attempt to…

Machine Learning · Computer Science 2022-02-01 Minjia Zhang , Niranjan Uma Naresh , Yuxiong He

In this paper, we develop a new accelerated stochastic gradient method for efficiently solving the convex regularized empirical risk minimization problem in mini-batch settings. The use of mini-batches is becoming a golden standard in the…

Optimization and Control · Mathematics 2017-09-20 Tomoya Murata , Taiji Suzuki

Stochastic Gradient Descent (SGD) and its variants are almost universally used to train neural networks and to fit a variety of other parametric models. An important hyperparameter in this context is the batch size, which determines how…

Optimization and Control · Mathematics 2023-12-05 Stefan Perko

Training deep neural networks (DNNs) used in modern machine learning is computationally expensive. Machine learning scientists, therefore, rely on stochastic first-order methods for training, coupled with significant hand-tuning, to obtain…

Machine Learning · Computer Science 2023-07-24 Eric Silk , Swarnita Chakraborty , Nairanjana Dasgupta , Anand D. Sarwate , Andrew Lumsdaine , Tony Chiang

This paper presents Rudra, a parameter server based distributed computing framework tuned for training large-scale deep neural networks. Using variants of the asynchronous stochastic gradient descent algorithm we study the impact of…

Machine Learning · Statistics 2016-12-07 Suyog Gupta , Wei Zhang , Fei Wang

The susceptibility of deep neural networks (DNNs) to adversarial examples has prompted an increase in the deployment of adversarial attacks. Image-agnostic universal adversarial perturbations (UAPs) are much more threatening, but many…

Computer Vision and Pattern Recognition · Computer Science 2023-08-15 Geunhyeok Yu , Minwoo Jeon , Hyoseok Hwang

It is a well-known fact that the performance of deep learning models deteriorates when they encounter a distribution shift at test time. Test-time adaptation (TTA) algorithms have been proposed to adapt the model online while inferring test…

Computer Vision and Pattern Recognition · Computer Science 2023-12-15 Jayeon Yoo , Dongkwan Lee , Inseop Chung , Donghyun Kim , Nojun Kwak

In this paper, we consider multi-stage stochastic optimization problems with convex objectives and conic constraints at each stage. We present a new stochastic first-order method, namely the dynamic stochastic approximation (DSA) algorithm,…

Optimization and Control · Mathematics 2019-08-22 Guanghui Lan , Zhiqiang Zhou

Despite plenty of efforts focusing on improving the domain adaptation ability (DA) under unsupervised or few-shot semi-supervised settings, recently the solution of active learning started to attract more attention due to its suitability in…

Machine Learning · Computer Science 2022-04-05 Ming Xie , Yuxi Li , Yabiao Wang , Zekun Luo , Zhenye Gan , Zhongyi Sun , Mingmin Chi , Chengjie Wang , Pei Wang

As deep learning models and datasets rapidly scale up, network training is extremely time-consuming and resource-costly. Instead of training on the entire dataset, learning with a small synthetic dataset becomes an efficient solution.…

Machine Learning · Computer Science 2022-08-02 Zixuan Jiang , Jiaqi Gu , Mingjie Liu , David Z. Pan

Block coordinate descent methods and stochastic subgradient methods have been extensively studied in optimization and machine learning. By combining randomized block sampling with stochastic subgradient methods based on dual averaging, we…

Optimization and Control · Mathematics 2015-09-16 Qi Deng , Guanghui Lan , Anand Rangarajan

Background: Deep learning models are typically trained using stochastic gradient descent or one of its variants. These methods update the weights using their gradient, estimated from a small fraction of the training data. It has been…

Machine Learning · Statistics 2018-01-03 Elad Hoffer , Itay Hubara , Daniel Soudry