中文
相关论文

相关论文: Revisiting Gradient Clipping: Stochastic bias and …

200 篇论文

Stochastic gradient descent is one of the most successful approaches for solving large-scale problems, especially in machine learning and statistics. At each iteration, it employs an unbiased estimator of the full gradient computed from one…

数值分析 · 数学 2018-12-05 Bangti Jin , Xiliang Lu

Recently there are a considerable amount of work devoted to the study of the algorithmic stability and generalization for stochastic gradient descent (SGD). However, the existing stability analysis requires to impose restrictive assumptions…

机器学习 · 计算机科学 2020-06-16 Yunwen Lei , Yiming Ying

In this work we study high probability bounds for stochastic subgradient methods under heavy tailed noise. In this setting the noise is only assumed to have finite variance as opposed to a sub-Gaussian distribution for which it is known…

最优化与控制 · 数学 2024-04-16 Daniela A. Parletta , Andrea Paudice , Massimiliano Pontil , Saverio Salzo

Differentially Private Stochastic Gradient Descent (DPSGD) is widely utilized to preserve training data privacy in deep learning, which first clips the gradients to a predefined norm and then injects calibrated noise into the training…

机器学习 · 计算机科学 2024-05-29 Haichao Sha , Yang Cao , Yong Liu , Yuncheng Wu , Ruixuan Liu , Hong Chen

Stochastic gradient descent (SGD) is a powerful optimization technique that is particularly useful in online learning scenarios. Its convergence analysis is relatively well understood under the assumption that the data samples are…

机器学习 · 计算机科学 2024-10-03 Ethan Che , Jing Dong , Xin T. Tong

Differentially private stochastic gradient descent (DP-SGD) is the most widely used method for training machine learning models with provable privacy guarantees. A key challenge in DP-SGD is setting the per-sample gradient clipping…

机器学习 · 计算机科学 2025-10-29 Atefeh Gilani , Naima Tasnim , Lalitha Sankar , Oliver Kosut

Differential privacy (DP) has become an essential framework for privacy-preserving machine learning. Existing DP learning methods, however, often have disparate impacts on model predictions, e.g., for minority groups. Gradient clipping,…

机器学习 · 计算机科学 2025-06-03 Linzh Zhao , Aki Rehn , Mikko A. Heikkilä , Razane Tajeddine , Antti Honkela

Modern machine learning is dominated by complex, overparameterized architectures capable of interpolating data and achieving zero training loss. For such models, we investigate the convergence properties of two popular modifications to…

最优化与控制 · 数学 2026-05-27 Aleksandr Lobanov , Anastasia Koloskova

In the machine learning literature stochastic gradient descent has recently been widely discussed for its purported implicit regularization properties. Much of the theory, that attempts to clarify the role of noise in stochastic gradient…

机器学习 · 计算机科学 2022-10-21 Alberto Lanconelli , Christopher S. A. Lauria

The problem of stopping stochastic gradient descent (SGD) in an online manner, based solely on the observed trajectory, is a challenging theoretical problem with significant consequences for applications. While SGD is routinely monitored as…

最优化与控制 · 数学 2026-02-24 Liviu Aolaritei , Michael I. Jordan

Stochastic Gradient Descent (SGD) is a cornerstone of large-scale optimization, yet its theoretical behavior under heavy-tailed noise -- common in modern machine learning and reinforcement learning -- remains poorly understood. In this…

最优化与控制 · 数学 2025-08-08 Ilyas Fatkhullin , Florian Hübler , Guanghui Lan

While stochastic gradient descent (SGD) is still the \emph{de facto} algorithm in deep learning, adaptive methods like Clipped SGD/Adam have been observed to outperform SGD across important tasks, such as attention models. The settings…

Low-precision training has become crucial for reducing the computational and memory costs of large-scale deep learning. However, quantizing gradients introduces magnitude shrinkage, which can change how stochastic gradient descent (SGD)…

机器学习 · 计算机科学 2026-01-09 Vincent-Daniel Yun

Stochastic gradient algorithms are the main focus of large-scale optimization problems and led to important successes in the recent advancement of the deep learning algorithms. The convergence of SGD depends on the careful choice of…

机器学习 · 计算机科学 2017-03-03 Caglar Gulcehre , Jose Sotelo , Marcin Moczulski , Yoshua Bengio

Importance sampling has become an indispensable strategy to speed up optimization algorithms for large-scale applications. Improved adaptive variants - using importance values defined by the complete gradient information which changes…

机器学习 · 计算机科学 2017-11-08 Sebastian U. Stich , Anant Raj , Martin Jaggi

Stochastic gradient descent is one of the most common iterative algorithms used in machine learning and its convergence analysis is a rich area of research. Understanding its convergence properties can help inform what modifications of it…

最优化与控制 · 数学 2025-11-25 Liam Madden , Emiliano Dall'Anese , Stephen Becker

There are several applications of stochastic optimization where one can benefit from a robust estimate of the gradient. For example, domains such as distributed learning with corrupted nodes, the presence of large outliers in the training…

机器学习 · 统计学 2025-10-30 Fabian Schaipp , Guillaume Garrigos , Umut Simsekli , Robert Gower

Stochastic-approximation gradient methods are attractive for large-scale convex optimization because they offer inexpensive iterations. They are especially popular in data-fitting and machine-learning applications where the data arrives in…

最优化与控制 · 数学 2014-01-09 Michael P. Friedlander , Gabriel Goh

Differentially Private Stochastic Gradient Descent (DP-SGD) is a widely adopted technique for privacy-preserving deep learning. A critical challenge in DP-SGD is selecting the optimal clipping threshold C, which involves balancing the…

机器学习 · 计算机科学 2025-04-02 Chengkun Wei , Weixian Li , Chen Gong , Wenzhi Chen

Stochastic gradient descent (SGD) still is the workhorse for many practical problems. However, it converges slow, and can be difficult to tune. It is possible to precondition SGD to accelerate its convergence remarkably. But many attempts…

机器学习 · 统计学 2017-02-23 Xi-Lin Li