English
Related papers

Related papers: An Unconstrained Layer-Peeled Perspective on Neura…

200 papers

We prove that the global minimum of the backpropagation (BP) training problem of neural networks with an arbitrary nonlinear activation is given by the ridgelet transform. A series of computational experiments show that there exists an…

Machine Learning · Statistics 2019-01-31 Sho Sonoda , Isao Ishikawa , Masahiro Ikeda , Kei Hagihara , Yoshihiro Sawano , Takuo Matsubara , Noboru Murata

Recent theoretical work has demonstrated that deep neural networks have superior performance over shallow networks, but their training is more difficult, e.g., they suffer from the vanishing gradient problem. This problem can be typically…

Machine Learning · Statistics 2021-11-03 Lu Lu , Yanhui Su , George Em Karniadakis

The dynamics of gradient-based training in neural networks often exhibit nontrivial structures; hence, understanding them remains a central challenge in theoretical machine learning. In particular, a concept of feature unlearning, in which…

Machine Learning · Computer Science 2026-02-10 Shota Imai , Sota Nishiyama , Masaaki Imaizumi

Coordinate-based neural networks parameterizing implicit surfaces have emerged as efficient representations of geometry. They effectively act as parametric level sets with the zero-level set defining the surface of interest. We present a…

Computer Vision and Pattern Recognition · Computer Science 2022-07-22 Ishit Mehta , Manmohan Chandraker , Ravi Ramamoorthi

Neural networks are typically trained with a single learning rate across all layers. While recent empirical evidence suggests that assigning layer-specific learning rates can accelerate training, a principled understanding of the conditions…

Machine Learning · Computer Science 2026-05-26 Sihan Zeng , Sujay Bhatt , Sumitra Ganesh

Learning in Deep Neural Networks (DNN) takes place by minimizing a non-convex high-dimensional loss function, typically by a stochastic gradient descent (SGD) strategy. The learning process is observed to be able to find good minimizers…

Machine Learning · Computer Science 2020-03-12 Carlo Baldassi , Fabrizio Pittorino , Riccardo Zecchina

We analyze multi-layer neural networks in the asymptotic regime of simultaneously (A) large network sizes and (B) large numbers of stochastic gradient descent training iterations. We rigorously establish the limiting behavior of the…

Probability · Mathematics 2021-04-06 Justin Sirignano , Konstantinos Spiliopoulos

We prove the converse of the universal approximation theorem, i.e. a neural network (NN) encoding theorem which shows that for every stably converged NN of continuous activation functions, its weight matrix actually encodes a continuous…

Machine Learning · Computer Science 2023-09-13 Ng Shyh-Chang , A-Li Luo , Bo Qiu

Modern machine learning models are often trained in a setting where the number of parameters exceeds the number of training samples. To understand the implicit bias of gradient descent in such overparameterized models, prior work has…

Machine Learning · Statistics 2025-10-29 Hannes Matt , Dominik Stöger

We present a unified theoretical framework connecting the first property of Deep Neural Collapse (DNC1) to the emergence of implicit low-rank bias in nonlinear networks trained with $L^2$ weight decay regularization. Our main contributions…

Machine Learning · Computer Science 2026-02-12 Emanuele Zangrando , Piero Deidda , Simone Brugiapaglia , Nicola Guglielmi , Francesco Tudisco

Effective LLM training depends on predictable scaling of key quantities -- such as final loss and optimal hyperparameters -- with model and dataset size. Qiu et al. (2025) recently showed that this predictability can extend beyond scalars:…

Machine Learning · Computer Science 2026-03-03 Shane Bergsma , Bin Claire Zhang , Nolan Dey , Shaheer Muhammad , Gurpreet Gosal , Joel Hestness

The rapid adoption of synthetic data for training Large Language Models (LLMs) has introduced the technical challenge of "model collapse"-a degenerative process where recursive training on model-generated content leads to a contraction of…

Machine Learning · Computer Science 2026-03-24 Yi Gu , Lingyou Pang , Xiangkun Ye , Tianyu Wang , Jianyu Lin , Carey E. Priebe , Alexander Aue

The ability to predict future states of the environment is a central pillar of intelligence. At its core, effective prediction requires an internal model of the world and an understanding of the rules by which the world changes. Here, we…

Machine Learning · Computer Science 2016-01-21 William Lotter , Gabriel Kreiman , David Cox

To mitigate societal biases implicitly encoded in recent successful pretrained language models, a diverse array of approaches have been proposed to encourage model fairness, focusing on prompting, data augmentation, regularized fine-tuning,…

Computation and Language · Computer Science 2025-01-30 Jingxuan Xu , Wuyang Chen , Linyi Li , Yao Zhao , Yunchao Wei

Continual learning (CL) aims to learn a sequence of tasks without forgetting the previously acquired knowledge. However, recent CL advances are restricted to supervised continual learning (SCL) scenarios. Consequently, they are not scalable…

Machine Learning · Computer Science 2022-04-06 Divyam Madaan , Jaehong Yoon , Yuanchun Li , Yunxin Liu , Sung Ju Hwang

In this paper, we perform the convergence analysis of unsupervised Legendre--Galerkin neural networks (ULGNet), a deep-learning-based numerical method for solving partial differential equations (PDEs). Unlike existing deep learning-based…

Numerical Analysis · Mathematics 2022-11-17 Seungchan Ko , Seok-Bae Yun , Youngjoon Hong

A candidate explanation of the good empirical performance of deep neural networks is the implicit regularization effect of first order optimization methods. Inspired by this, we prove a convergence theorem for nonconvex composite…

Machine Learning · Computer Science 2023-02-14 Dávid Terjék , Diego González-Sánchez

Large language models (LLMs) are pretrained by minimizing the cross-entropy loss for next-token prediction. In this paper, we study whether this optimization strategy can induce geometric structure in the learned model weights and context…

Optimization and Control · Mathematics 2026-05-14 Zhehang Du , Hangfeng He , Weijie Su

Neural networks are powerful models that solve a variety of complex real-world problems. However, the stochastic nature of training and large number of parameters in a typical neural model makes them difficult to evaluate via inspection.…

Machine Learning · Computer Science 2021-04-22 John Clemens

While deep learning models and techniques have achieved great empirical success, our understanding of the source of success in many aspects remains very limited. In an attempt to bridge the gap, we investigate the decision boundary of a…

Neural and Evolutionary Computing · Computer Science 2019-01-03 Yu Li , Lizhong Ding , Xin Gao
‹ Prev 1 4 5 6 7 8 10 Next ›