English
Related papers

Related papers: Effect of Depth and Width on Local Minima in Deep …

200 papers

It is widely believed that a neural network can fit a training set containing at least as many samples as it has parameters, underpinning notions of overparameterized and underparameterized models. In practice, however, we only find…

Machine Learning · Computer Science 2024-06-18 Ravid Shwartz-Ziv , Micah Goldblum , Arpit Bansal , C. Bayan Bruss , Yann LeCun , Andrew Gordon Wilson

Training deep neural networks for classification often includes minimizing the training loss beyond the zero training error point. In this phase of training, a "neural collapse" behavior has been observed: the variability of features…

Machine Learning · Computer Science 2023-05-30 Tom Tirer , Haoxiang Huang , Jonathan Niles-Weed

We explore some mathematical features of the loss landscape of overparameterized neural networks. A priori one might imagine that the loss function looks like a typical function from $\mathbb{R}^n$ to $\mathbb{R}$ - in particular,…

Machine Learning · Computer Science 2018-04-27 Y Cooper

Recent numerical experiments have demonstrated that the choice of optimization geometry used during training can impact generalization performance when learning expressive nonlinear model classes such as deep neural networks. These…

Machine Learning · Computer Science 2022-04-25 Nicholas M. Boffi , Stephen Tu , Jean-Jacques E. Slotine

It is widely believed that natural image data exhibits low-dimensional structure despite the high dimensionality of conventional pixel representations. This idea underlies a common intuition for the remarkable success of deep learning in…

Computer Vision and Pattern Recognition · Computer Science 2021-04-20 Phillip Pope , Chen Zhu , Ahmed Abdelkader , Micah Goldblum , Tom Goldstein

The skip-connections used in residual networks have become a standard architecture choice in deep learning due to the increased training stability and generalization performance with this architecture, although there has been limited…

Machine Learning · Computer Science 2019-10-08 Spencer Frei , Yuan Cao , Quanquan Gu

Finding parameters in a deep neural network (NN) that fit training data is a nonconvex optimization problem, but a basic first-order optimization method (gradient descent) finds a global optimizer with perfect fit (zero-loss) in many…

Machine Learning · Computer Science 2025-03-07 Zhiyan Ding , Shi Chen , Qin Li , Stephen Wright

Structured pruning compresses neural networks by reducing channels (filters) for fast inference and low footprint at run-time. To restore accuracy after pruning, fine-tuning is usually applied to pruned networks. However, too few remaining…

Computer Vision and Pattern Recognition · Computer Science 2024-01-01 Yu Qian , Jian Cao , Xiaoshuang Li , Jie Zhang , Hufei Li , Jue Chen

We study the effect of normalization on the layers of deep neural networks of feed-forward type. A given layer $i$ with $N_{i}$ hidden units is allowed to be normalized by $1/N_{i}^{\gamma_{i}}$ with $\gamma_{i}\in[1/2,1]$ and we study the…

Machine Learning · Computer Science 2022-09-05 Jiahui Yu , Konstantinos Spiliopoulos

Deep neural networks (DNNs) achieve impressive results for complicated tasks like object detection on images and speech recognition. Motivated by this practical success, there is now a strong interest in showing good theoretical properties…

Machine Learning · Statistics 2020-06-16 Michael Kohler , Adam Krzyzak , Sophie Langer

When training deep neural networks with gradient descent, sharpness often increases -- a phenomenon known as progressive sharpening -- before saturating at the edge of stability. Although commonly observed in practice, the underlying…

Machine Learning · Computer Science 2025-06-10 Geonhui Yoo , Minhak Song , Chulhee Yun

Deep learning models trained on large data sets have been widely successful in both vision and language domains. As state-of-the-art deep learning architectures have continued to grow in parameter count so have the compute budgets and times…

This work finds the analytical expression of the global minima of a deep linear network with weight decay and stochastic neurons, a fundamental model for understanding the landscape of neural networks. Our result implies that the origin is…

Machine Learning · Statistics 2023-06-14 Liu Ziyin , Botao Li , Xiangming Meng

It is well known that (stochastic) gradient descent has an implicit bias towards flat minima. In deep neural network training, this mechanism serves to screen out minima. However, the precise effect that this has on the trained network is…

Machine Learning · Computer Science 2020-08-11 Rotem Mulayoff , Tomer Michaeli

We study the high-dimensional training dynamics of a shallow neural network with quadratic activation in a teacher-student setup. We focus on the extensive-width regime, where the teacher and student network widths scale proportionally with…

Optimization and Control · Mathematics 2026-01-16 Simon Martin , Giulio Biroli , Francis Bach

Recent works have demonstrated that increasing model capacity through width in over-parameterized neural networks leads to a decrease in test risk. For neural networks, however, model capacity can also be increased through depth, yet…

Machine Learning · Computer Science 2021-06-08 Eshaan Nichani , Adityanarayanan Radhakrishnan , Caroline Uhler

Deep representation learning using triplet network for classification suffers from a lack of theoretical foundation and difficulty in tuning both the network and classifiers for performance. To address the problem, local-margin triplet loss…

Computer Vision and Pattern Recognition · Computer Science 2019-11-20 Phawis Thammasorn , Daniel Hippe , Wanpracha Chaovalitwongse , Matthew Spraker , Landon Wootton , Matthew Nyflot , Stephanie Combs , Jan Peeken , Eric Ford

Modern deep learning models are over-parameterized, where the optimization setup strongly affects the generalization performance. A key element of reliable optimization for these systems is the modification of the loss function.…

Machine Learning · Computer Science 2022-12-09 Kayhan Behdin , Qingquan Song , Aman Gupta , David Durfee , Ayan Acharya , Sathiya Keerthi , Rahul Mazumder

Understanding generalization in deep neural networks is an active area of research. A promising avenue of exploration has been that of margin measurements: the shortest distance to the decision boundary for a given sample or that sample's…

Machine Learning · Computer Science 2024-05-29 Coenraad Mouton

Deep learning is recognized to be capable of discovering deep features for representation learning and pattern recognition without requiring elegant feature engineering techniques by taking advantage of human ingenuity and prior knowledge.…

Machine Learning · Computer Science 2020-04-02 Zhi Han , Siquan Yu , Shao-Bo Lin , Ding-Xuan Zhou