English
Related papers

Related papers: Implicit Bias of MSE Gradient Optimization in Unde…

200 papers

Negative sampling (NS) loss plays an important role in learning knowledge graph embedding (KGE) to handle a huge number of entities. However, the performance of KGE degrades without hyperparameters such as the margin term and number of…

Machine Learning · Computer Science 2022-07-08 Hidetaka Kamigaito , Katsuhiko Hayashi

Despite their prevalence in deep-learning communities, over-parameterized models convey high demands of computational costs for proper training. This work studies the fine-grained, modular-level learning dynamics of over-parameterized…

The Neural Tangent Kernel (NTK) is the wide-network limit of a kernel defined using neural networks at initialization, whose embedding is the gradient of the output of the network with respect to its parameters. We study the "after kernel",…

Machine Learning · Computer Science 2021-12-14 Philip M. Long

Physics-informed neural networks (PINNs) are demonstrating remarkable promise in integrating physical models with gappy and noisy observational data, but they still struggle in cases where the target functions to be approximated exhibit…

Machine Learning · Computer Science 2021-06-16 Sifan Wang , Hanwen Wang , Paris Perdikaris

We prove the precise scaling, at finite depth and width, for the mean and variance of the neural tangent kernel (NTK) in a randomly initialized ReLU network. The standard deviation is exponential in the ratio of network depth to width.…

Machine Learning · Computer Science 2019-09-16 Boris Hanin , Mihai Nica

Wide neural networks are biased towards learning certain functions, influencing both the rate of convergence of gradient descent (GD) and the functions that are reachable with GD in finite training time. As such, there is a great need for…

Machine Learning · Computer Science 2024-03-21 Amnon Geifman , Daniel Barzilai , Ronen Basri , Meirav Galun

Characterization of quantum objects, being them states, processes, or measurements, complemented by previous knowledge about them is a valuable approach, especially as it leads to routine procedures for real-life components. To this end,…

Quantum Physics · Physics 2023-06-28 Massimiliano Guarneri , Ilaria Gianani , Marco Barbieri , Andrea Chiuri

In this paper, we develop a new optimization framework for the least squares learning problem via fully connected neural networks or physics-informed neural networks. The gradient descent sometimes behaves inefficiently in deep learning…

Machine Learning · Computer Science 2025-05-01 Yaru Liu , Yiqi Gu , Michael K. Ng

Inverse problems and, in particular, inferring unknown or latent parameters from data are ubiquitous in engineering simulations. A predominant viewpoint in identifying unknown parameters is Bayesian inference where both prior information…

Computation · Statistics 2022-08-31 Vahid Keshavarzzadeh , Robert M. Kirby , Akil Narayan

We study the implicit regularization of gradient descent towards structured sparsity via a novel neural reparameterization, which we call a diagonally grouped linear neural network. We show the following intriguing property of our…

Machine Learning · Statistics 2023-01-31 Jiangyuan Li , Thanh V. Nguyen , Chinmay Hegde , Raymond K. W. Wong

This paper investigates typical behaviors like damped oscillations in fractional order (FO) dynamical systems. Such response occurs due to the presence of, what is conceived as, pseudo-damping and meta-damping in some special class of FO…

Systems and Control · Computer Science 2012-08-02 Saptarshi Das , Indranil Pan , Khrist Sur , Shantanu Das

Graph convolutional networks (GCNs) and their variants have achieved great success in dealing with graph-structured data. Nevertheless, it is well known that deep GCNs suffer from the over-smoothing problem, where node representations tend…

Machine Learning · Computer Science 2022-04-22 Wei Huang , Yayong Li , Weitao Du , Jie Yin , Richard Yi Da Xu , Ling Chen , Miao Zhang

A fundamental property of deep learning normalization techniques, such as batch normalization, is making the pre-normalization parameters scale invariant. The intrinsic domain of such parameters is the unit sphere, and therefore their…

Machine Learning · Computer Science 2023-01-18 Maxim Kodryan , Ekaterina Lobacheva , Maksim Nakhodnov , Dmitry Vetrov

We study the implicit bias of the general family of steepest descent algorithms with infinitesimal learning rate in deep homogeneous neural networks. We show that: (a) an algorithm-dependent geometric margin starts increasing once the…

Machine Learning · Computer Science 2025-09-23 Nikolaos Tsilivis , Eitan Gronich , Julia Kempe , Gal Vardi

Deep learning methods operate in regimes that defy the traditional statistical mindset. Neural network architectures often contain more parameters than training samples, and are so rich that they can interpolate the observed labels, even if…

Statistics Theory · Mathematics 2020-12-14 Song Mei , Andrea Montanari

The classical statistical learning theory implies that fitting too many parameters leads to overfitting and poor performance. That modern deep neural networks generalize well despite a large number of parameters contradicts this finding and…

Machine Learning · Statistics 2022-10-18 Masaaki Imaizumi , Johannes Schmidt-Hieber

Physics-informed neural network (PINN) algorithms have shown promising results in solving a wide range of problems involving partial differential equations (PDEs). However, they often fail to converge to desirable solutions when the target…

Machine Learning · Computer Science 2022-07-01 Ghazal Farhani , Alexander Kazachek , Boyu Wang

State-of-the-art training algorithms for deep learning models are based on stochastic gradient descent (SGD). Recently, many variations have been explored: perturbing parameters for better accuracy (such as in Extragradient), limiting SGD…

Machine Learning · Computer Science 2022-03-23 Amirkeivan Mohtashami , Martin Jaggi , Sebastian U. Stich

Model Reprogramming (MR) is a resource-efficient framework that adapts large pre-trained models to new tasks with minimal additional parameters and data, offering a promising solution to the challenges of training large models for diverse…

Machine Learning · Computer Science 2025-06-03 Ming-Yu Chung , Jiashuo Fan , Hancheng Ye , Qinsi Wang , Wei-Chen Shen , Chia-Mu Yu , Pin-Yu Chen , Sy-Yen Kuo

The dynamics of DNNs during gradient descent is described by the so-called Neural Tangent Kernel (NTK). In this article, we show that the NTK allows one to gain precise insight into the Hessian of the cost of DNNs. When the NTK is fixed…

Machine Learning · Computer Science 2020-02-11 Arthur Jacot , Franck Gabriel , Clément Hongler