English
Related papers

Related papers: Large Learning Rate Tames Homogeneity: Convergence…

200 papers

Meta-learning that uses implicit gradient have provided an exciting alternative to standard techniques which depend on the trajectory of the inner loop training. Implicit meta-learning (IML), however, require computing $2^{nd}$ order…

Machine Learning · Computer Science 2023-10-31 Fady Rezk

The choice of initial learning rate can have a profound effect on the performance of deep networks. We present a class of neural networks with solvable training dynamics, and confirm their predictions empirically in practical deep learning…

Machine Learning · Statistics 2020-03-05 Aitor Lewkowycz , Yasaman Bahri , Ethan Dyer , Jascha Sohl-Dickstein , Guy Gur-Ari

Traditional analyses of gradient descent optimization show that, when the largest eigenvalue of the loss Hessian - often referred to as the sharpness - is below a critical learning-rate threshold, then training is 'stable' and training loss…

Machine Learning · Computer Science 2024-12-24 Lawrence Wang , Stephen J. Roberts

We study the problem of learning-to-learn: inferring a learning algorithm that works well on tasks sampled from an unknown distribution. As class of algorithms we consider Stochastic Gradient Descent on the true risk regularized by the…

Machine Learning · Computer Science 2019-03-26 Giulia Denevi , Carlo Ciliberto , Riccardo Grazzi , Massimiliano Pontil

Continual learning, focused on sequentially learning multiple tasks, has gained significant attention recently. Despite the tremendous progress made in the past, the theoretical understanding, especially factors contributing to catastrophic…

Machine Learning · Computer Science 2024-05-29 Meng Ding , Kaiyi Ji , Di Wang , Jinhui Xu

Adaptive optimization methods (such as Adam) play a major role in LLM pretraining, significantly outperforming Gradient Descent (GD). Recent studies have proposed new smoothness assumptions on the loss function to explain the advantages of…

Machine Learning · Computer Science 2025-12-02 Robin Yadav , Shuo Xie , Tianhao Wang , Zhiyuan Li

The performance of an optimizer on large-scale deep learning models depends critically on fine-tuning the learning rate, often requiring an extensive grid search over base learning rates, schedules, and other hyperparameters. In this paper,…

Machine Learning · Computer Science 2025-06-11 Ruichen Jiang , Ali Kavis , Aryan Mokhtari

It is generally accepted that starting neural networks training with large learning rates (LRs) improves generalization. Following a line of research devoted to understanding this effect, we conduct an empirical study in a controlled…

Machine Learning · Computer Science 2024-10-30 Ildus Sadrtdinov , Maxim Kodryan , Eduard Pokonechny , Ekaterina Lobacheva , Dmitry Vetrov

Gradient descent dynamics on the deep matrix factorization problem is extensively studied as a simplified theoretical model for deep neural networks. Although the convergence theory for two-layer matrix factorization is well-established, no…

Optimization and Control · Mathematics 2025-11-20 Minrui Luo , Weihang Xu , Xiang Gao , Maryam Fazel , Simon Shaolei Du

Recent research has observed that in machine learning optimization, gradient descent (GD) often operates at the edge of stability (EoS) [Cohen, et al., 2021], where the stepsizes are set to be large, resulting in non-monotonic losses…

Machine Learning · Computer Science 2023-10-17 Jingfeng Wu , Vladimir Braverman , Jason D. Lee

Batch Normalization (BN) has become a cornerstone of deep learning across diverse architectures, appearing to help optimization as well as generalization. While the idea makes intuitive sense, theoretical analysis of its effectiveness has…

Machine Learning · Computer Science 2018-12-11 Sanjeev Arora , Zhiyuan Li , Kaifeng Lyu

Continual learning, the ability of a model to adapt to an ongoing sequence of tasks without forgetting earlier ones, is a central goal of artificial intelligence. To better understand its underlying mechanisms, we study the limitations of…

Machine Learning · Statistics 2026-04-21 Hossein Taheri , Avishek Ghosh , Arya Mazumdar

Stochastic Gradient Descent (SGD) and its variants are mainstream methods for training deep networks in practice. SGD is known to find a flat minimum that often generalizes well. However, it is mathematically unclear how deep learning can…

Machine Learning · Computer Science 2021-01-18 Zeke Xie , Issei Sato , Masashi Sugiyama

Traditional analyses of gradient descent show that when the largest eigenvalue of the Hessian, also known as the sharpness $S(\theta)$, is bounded by $2/\eta$, training is "stable" and the training loss decreases monotonically. Recent…

Machine Learning · Computer Science 2023-04-12 Alex Damian , Eshaan Nichani , Jason D. Lee

Aimed at explaining the surprisingly good generalization behavior of overparameterized deep networks, recent works have developed a variety of generalization bounds for deep learning, all based on the fundamental learning-theoretic…

Machine Learning · Computer Science 2021-10-19 Vaishnavh Nagarajan , J. Zico Kolter

We empirically demonstrate that full-batch gradient descent on neural network training objectives typically operates in a regime we call the Edge of Stability. In this regime, the maximum eigenvalue of the training loss Hessian hovers just…

Machine Learning · Computer Science 2022-11-24 Jeremy M. Cohen , Simran Kaur , Yuanzhi Li , J. Zico Kolter , Ameet Talwalkar

We examine gradient descent on unregularized logistic regression problems, with homogeneous linear predictors on linearly separable datasets. We show the predictor converges to the direction of the max-margin (hard margin SVM) solution. The…

Machine Learning · Statistics 2024-10-29 Daniel Soudry , Elad Hoffer , Mor Shpigel Nacson , Suriya Gunasekar , Nathan Srebro

Stagewise training strategy is widely used for learning neural networks, which runs a stochastic algorithm (e.g., SGD) starting with a relatively large step size (aka learning rate) and geometrically decreasing the step size after a number…

Machine Learning · Statistics 2019-02-05 Zhuoning Yuan , Yan Yan , Rong Jin , Tianbao Yang

In overparametrized models, the noise in stochastic gradient descent (SGD) implicitly regularizes the optimization trajectory and determines which local minimum SGD converges to. Motivated by empirical studies that demonstrate that training…

Machine Learning · Computer Science 2021-12-07 Alex Damian , Tengyu Ma , Jason D. Lee

We consider linear prediction with a convex Lipschitz loss, or more generally, stochastic convex optimization problems of generalized linear form, i.e.~where each instantaneous loss is a scalar convex function of a linear function. We show…

Machine Learning · Computer Science 2022-11-01 Idan Amir , Roi Livni , Nathan Srebro