English
Related papers

Related papers: Per-Example Gradient Regularization Improves Learn…

200 papers

Noisy training data can significantly degrade the performance of language-model-based classifiers, particularly in non-topical classification tasks. In this study we designed a methodological framework to assess the impact of denoising.…

Computation and Language · Computer Science 2026-03-10 Nouran Khallaf , Serge Sharoff

Distributed training of massive machine learning models, in particular deep neural networks, via Stochastic Gradient Descent (SGD) is becoming commonplace. Several families of communication-reduction methods, such as quantization,…

Machine Learning · Computer Science 2018-09-28 Dan Alistarh , Torsten Hoefler , Mikael Johansson , Sarit Khirirat , Nikola Konstantinov , Cédric Renggli

Training generative models with differential privacy (DP) typically involves injecting noise into gradient updates or adapting the discriminator's training procedure. As a result, such approaches often struggle with hyper-parameter tuning…

Machine Learning · Computer Science 2024-10-29 Kristjan Greenewald , Yuancheng Yu , Hao Wang , Kai Xu

Giving up and starting over may seem wasteful in many situations such as searching for a target or training deep neural networks (DNNs). Our study, though, demonstrates that resetting from a checkpoint can significantly improve…

Machine Learning · Computer Science 2025-03-14 Youngkyoung Bae , Yeongwoo Song , Hawoong Jeong

Certified machine unlearning can be achieved via noise injection leading to differential privacy guarantees, where noise is calibrated to worst-case sensitivity. Such conservative calibration often results in performance degradation,…

Machine Learning · Computer Science 2026-05-25 Hanna Benarroch , Jamal Atif , Olivier Cappé

Differentially private stochastic gradient descent (DP-SGD) is the gold standard for training machine learning models with formal differential privacy guarantees. Several recent extensions improve its accuracy by introducing correlated…

Machine Learning · Computer Science 2026-05-13 Nikita P. Kalinin , Ryan McKenna , Rasmus Pagh , Christoph H. Lampert

Numerous empirical evidence has corroborated that the noise plays a crucial rule in effective and efficient training of neural networks. The theory behind, however, is still largely unknown. This paper studies this fundamental problem…

Machine Learning · Computer Science 2019-09-10 Mo Zhou , Tianyi Liu , Yan Li , Dachao Lin , Enlu Zhou , Tuo Zhao

In the era of noisy intermediate-scale quantum (NISQ), variational quantum circuits (VQCs) have been widely applied in various domains, demonstrating the potential advantages of quantum circuits over classical models. Similar to classic…

Quantum Physics · Physics 2025-08-26 Jun Zhuang , Jack Cunningham , Chaowen Guan

Deep neural networks have become popular in many supervised learning tasks, but they may suffer from overfitting when the training dataset is limited. To mitigate this, many researchers use data augmentation, which is a widely used and…

Machine Learning · Computer Science 2022-05-27 Jianhan Wu , Shijing Si , Jianzong Wang , Jing Xiao

Stochastic gradient descent (SGD) with momentum is widely used for training modern deep learning architectures. While it is well-understood that using momentum can lead to faster convergence rate in various settings, it has also been…

Machine Learning · Computer Science 2022-07-14 Samy Jelassi , Yuanzhi Li

It has long been argued that minibatch stochastic gradient descent can generalize better than large batch gradient descent in deep neural networks. However recent papers have questioned this claim, arguing that this effect is simply a…

Machine Learning · Computer Science 2020-06-29 Samuel L. Smith , Erich Elsen , Soham De

Training algorithms in deep learning usually treat a mini-batch of samples as a single object; they average gradients over the mini-batch, and then process the average in various ways. Computing other statistics beyond the average may have…

Machine Learning · Computer Science 2026-03-03 Vincent Roulet , Atish Agarwala

We analyze the effect of quantizing weights and activations of neural networks on their loss and derive a simple regularization scheme that improves robustness against post-training quantization. By training quantization-ready networks, our…

Machine Learning · Computer Science 2020-02-19 Milad Alizadeh , Arash Behboodi , Mart van Baalen , Christos Louizos , Tijmen Blankevoort , Max Welling

Normalization layers are widely used in deep neural networks to stabilize training. In this paper, we consider the training of convolutional neural networks with gradient descent on a single training example. This optimization problem…

Machine Learning · Computer Science 2019-07-24 Zhenwei Dai , Reinhard Heckel

Quantum neural networks (QNNs) use parameterized quantum circuits with data-dependent inputs and generate outputs through the evaluation of expectation values. Calculating these expectation values necessitates repeated circuit evaluations,…

Quantum Physics · Physics 2024-06-26 David A. Kreplin , Marco Roth

Consistency regularization (CR), which enforces agreement between model predictions on augmented views, has found recent benefits in automatic speech recognition [1]. In this paper, we propose the use of consistency regularization for audio…

Sound · Computer Science 2025-09-15 Shanmuka Sadhu , Weiran Wang

Parameter-efficient tunings (PETs) have demonstrated impressive performance and promising perspectives in training large models, while they are still confronted with a common problem: the trade-off between learning new content and…

Machine Learning · Computer Science 2024-07-18 Jingyang Qiao , Zhizhong Zhang , Xin Tan , Yanyun Qu , Wensheng Zhang , Zhi Han , Yuan Xie

Modern deep learning models generalize remarkably well in-distribution, despite being overparametrized and trained with little to no explicit regularization. Instead, current theory credits implicit regularization imposed by the choice of…

Machine Learning · Computer Science 2026-03-17 Jonathan Wenger , Beau Coker , Juraj Marusic , John P. Cunningham

The minibatch stochastic gradient descent method (SGD) is widely applied in deep learning due to its efficiency and scalability that enable training deep networks with a large volume of data. Particularly in the distributed setting, SGD is…

Machine Learning · Computer Science 2020-11-19 Qiwei Yuan , Weizhe Hua , Yi Zhou , Cunxi Yu

By ensuring differential privacy in the learning algorithms, one can rigorously mitigate the risk of large models memorizing sensitive training data. In this paper, we study two algorithms for this purpose, i.e., DP-SGD and DP-NSGD, which…

Machine Learning · Computer Science 2022-06-28 Xiaodong Yang , Huishuai Zhang , Wei Chen , Tie-Yan Liu