中文
相关论文

相关论文: Existence and Estimation of Critical Batch Size fo…

200 篇论文

Neural networks are vulnerable to adversarial attacks: adding well-crafted, imperceptible perturbations to their input can modify their output. Adversarial training is one of the most effective approaches to training robust models against…

机器学习 · 计算机科学 2023-08-09 Hadi M. Dolatabadi , Sarah Erfani , Christopher Leckie

This paper focuses on understanding how the generalization error scales with the amount of the training data for deep neural networks (DNNs). Existing techniques in statistical learning require computation of capacity measures, such as VC…

机器学习 · 计算机科学 2021-05-06 Devansh Bisla , Apoorva Nandini Saridena , Anna Choromanska

Generative Adversarial Networks (GANs) are the most popular image generation models that have achieved remarkable progress on various computer vision tasks. However, training instability is still one of the open problems for all GAN-based…

图像与视频处理 · 电气工程与系统科学 2022-07-20 Ziqiang Li , Pengfei Xia , Rentuo Tao , Hongjing Niu , Bin Li

We are interested in the design of generative networks. The training of these mathematical structures is mostly performed with the help of adversarial (min-max) optimization problems. We propose a simple methodology for constructing such…

机器学习 · 计算机科学 2021-07-16 Kalliopi Basioti , George V. Moustakides

Distributed training increases the number of batches processed per iteration either by scaling-out (adding more nodes) or scaling-up (increasing the batch-size). However, the largest configuration does not necessarily yield the best…

机器学习 · 计算机科学 2026-03-20 Sahil Tyagi , Feiyi Wang

Training deep learning models can be computationally expensive. Prior works have shown that increasing the batch size can potentially lead to better overall throughput. However, the batch size is frequently limited by the accelerator memory…

机器学习 · 计算机科学 2023-01-25 Muralidhar Andoorveedu , Zhanda Zhu , Bojian Zheng , Gennady Pekhimenko

Diffusion models have shown promising results in speech enhancement, using a task-adapted diffusion process for the conditional generation of clean speech given a noisy mixture. However, at test time, the neural network used for score…

音频与语音处理 · 电气工程与系统科学 2024-01-17 Bunlong Lay , Jean-Marie Lemercier , Julius Richter , Timo Gerkmann

In this paper, we show that Generative Adversarial Networks (GANs) suffer from catastrophic forgetting even when they are trained to approximate a single target distribution. We show that GAN training is a continual learning problem in…

机器学习 · 计算机科学 2020-03-24 Hoang Thanh-Tung , Truyen Tran

While leveraging additional training data is well established to improve adversarial robustness, it incurs the unavoidable cost of data collection and the heavy computation to train models. To mitigate the costs, we propose Guided…

计算机视觉与模式识别 · 计算机科学 2023-05-26 Salah Ghamizi , Jingfeng Zhang , Maxime Cordy , Mike Papadakis , Masashi Sugiyama , Yves Le Traon

Many variants of adversarial training have been proposed, with most research focusing on problems with relatively few classes. In this paper, we propose Two Head Adversarial Training (THAT), a two-stream adversarial learning network that is…

计算机视觉与模式识别 · 计算机科学 2021-03-26 Zuxuan Wu , Tom Goldstein , Larry S. Davis , Ser-Nam Lim

Estimating uncertainty for AI agents in real-world multi-turn tool-using interaction with humans is difficult because failures are often triggered by sparse critical episodes (e.g., looping, incoherent tool use, or user-agent…

人工智能 · 计算机科学 2026-02-13 Sina Tayebati , Divake Kumar , Nastaran Darabi , Davide Ettori , Ranganath Krishnan , Amit Ranjan Trivedi

Generative adversarial networks (GANs) are pow- erful generative models based on providing feed- back to a generative network via a discriminator network. However, the discriminator usually as- sesses individual samples. This prevents the…

机器学习 · 计算机科学 2018-06-20 Thomas Lucas , Corentin Tallec , Jakob Verbeek , Yann Ollivier

Multi-task learning (MTL) seeks to improve the generalized performance of learning specific tasks, exploiting useful information incorporated in related tasks. As a promising area, this paper studies an MTL-based control approach…

系统与控制 · 电气工程与系统科学 2024-08-01 Andres Arias , Chuangchuang Sun

When training neural networks, it has been widely observed that a large step size is essential in stochastic gradient descent (SGD) for obtaining superior models. However, the effect of large step sizes on the success of SGD is not well…

机器学习 · 计算机科学 2023-02-17 Amirkeivan Mohtashami , Martin Jaggi , Sebastian Stich

GANs excel at learning high dimensional distributions, but they can update generator parameters in directions that do not correspond to the steepest descent direction of the objective. Prominent examples of problematic update directions…

机器学习 · 计算机科学 2018-06-08 Calvin Seward , Thomas Unterthiner , Urs Bergmann , Nikolay Jetchev , Sepp Hochreiter

We present Optimal Transport GAN (OT-GAN), a variant of generative adversarial nets minimizing a new metric measuring the distance between the generator distribution and the data distribution. This metric, which we call mini-batch energy…

机器学习 · 计算机科学 2018-03-16 Tim Salimans , Han Zhang , Alec Radford , Dimitris Metaxas

Generative Adversarial Networks (GANs) have recently attracted considerable attention in the AI community due to its ability to generate high-quality data of significant statistical resemblance to real data. Fundamentally, GAN is a game…

In recent years, Generative Adversarial Networks (GANs) have drawn a lot of attentions for learning the underlying distribution of data in various applications. Despite their wide applicability, training GANs is notoriously difficult. This…

机器学习 · 计算机科学 2019-04-23 Babak Barazandeh , Meisam Razaviyayn , Maziar Sanjabi

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…

机器学习 · 统计学 2019-03-05 Siyuan Ma , Mikhail Belkin

The choice of hyper-parameters affects the performance of neural models. While much previous research (Sutskever et al., 2013; Duchi et al., 2011; Kingma and Ba, 2015) focuses on accelerating convergence and reducing the effects of the…

计算与语言 · 计算机科学 2020-05-06 Hongfei Xu , Josef van Genabith , Deyi Xiong , Qiuhui Liu
‹ 上一页 1 8 9 10 下一页 ›