English
Related papers

Related papers: Gradient flow in parameter space is equivalent to …

200 papers

In this work, we analyze the relation between reparametrizations of gradient flow and the induced implicit bias in linear models, which encompass various basic regression tasks. In particular, we aim at understanding the influence of the…

Optimization and Control · Mathematics 2024-03-07 Hung-Hsu Chou , Johannes Maly , Dominik Stöger

We prove linear convergence of gradient descent to a global optimum for the training of deep residual networks with constant layer width and smooth activation function. We show that if the trained weights, as a function of the layer index,…

Machine Learning · Computer Science 2023-01-26 Rama Cont , Alain Rossier , RenYuan Xu

We investigate gradient descent training of wide neural networks and the corresponding implicit bias in function space. For univariate regression, we show that the solution of training a width-$n$ shallow ReLU network is within $n^{- 1/2}$…

Machine Learning · Statistics 2023-05-30 Hui Jin , Guido Montúfar

We consider a class of a nested optimization problems involving inner and outer objectives. We observe that by taking into explicit account the optimization dynamics for the inner objective it is possible to derive a general framework that…

Machine Learning · Statistics 2019-08-22 Luca Franceschi , Michele Donini , Paolo Frasconi , Massimiliano Pontil

In this paper we fully describe the trajectory of gradient flow over diagonal linear networks in the limit of vanishing initialisation. We show that the limiting flow successively jumps from a saddle of the training loss to another until…

Machine Learning · Computer Science 2023-10-26 Scott Pesme , Nicolas Flammarion

We study gradient flows for loss landscapes of fully connected feedforward neural networks with commonly used continuously differentiable activation functions such as the logistic, hyperbolic tangent, softplus or GELU function. We prove…

Machine Learning · Computer Science 2026-01-13 Julian Kranz , Davide Gallon , Steffen Dereich , Arnulf Jentzen

Computing the loss gradient via backpropagation consumes considerable energy during deep learning (DL) model training. In this paper, we propose a novel approach to efficiently compute DL models' gradients to mitigate the substantial energy…

Computer Vision and Pattern Recognition · Computer Science 2024-06-12 Challapalli Phanindra Revanth , Sumohana S. Channappayya , C Krishna Mohan

This paper develops expansive gradient dynamics in deep neural network-induced mapping spaces. Specifically, we generate tools and concepts for minimizing a class of energy functionals in an abstract Hilbert space setting covering a wide…

Optimization and Control · Mathematics 2025-07-21 Wolfgang Dahmen , Wuchen Li , Yuankai Teng , Zhu Wang

Algorithmic approaches endow deep learning systems with implicit bias that helps them generalize even in over-parametrized settings. In this paper, we focus on understanding such a bias induced in learning through dropout, a popular…

Machine Learning · Computer Science 2018-06-27 Poorya Mianjy , Raman Arora , Rene Vidal

We identify a class of over-parameterized deep neural networks with standard activation functions and cross-entropy loss which provably have no bad local valley, in the sense that from any point in parameter space there exists a continuous…

Machine Learning · Computer Science 2018-12-27 Quynh Nguyen , Mahesh Chandra Mukkamala , Matthias Hein

This article overviews how gradient flows, and discretizations thereof, are useful to design and analyze optimization and sampling algorithms. The interplay between optimization, sampling, and gradient flows is an active research area; our…

Computation · Statistics 2023-02-23 N. Garcia Trillos , B. Hosseini , D. Sanz-Alonso

Implicit deep learning has recently become popular in the machine learning community since these implicit models can achieve competitive performance with state-of-the-art deep networks while using significantly less memory and computational…

Machine Learning · Computer Science 2022-05-17 Tianxiang Gao , Hongyang Gao

A longstanding goal in deep learning research has been to precisely characterize training and generalization. However, the often complex loss landscapes of neural networks have made a theory of learning dynamics elusive. In this work, we…

Several recent works demonstrate that transformers can implement algorithms like gradient descent. By a careful construction of weights, these works show that multiple layers of transformers are expressive enough to simulate iterations of…

Machine Learning · Computer Science 2023-11-13 Kwangjun Ahn , Xiang Cheng , Hadi Daneshmand , Suvrit Sra

In this paper, we theoretically prove that gradient descent can find a global minimum of non-convex optimization of all layers for nonlinear deep neural networks of sizes commonly encountered in practice. The theory developed in this paper…

Machine Learning · Statistics 2020-06-18 Kenji Kawaguchi , Jiaoyang Huang

Gradient-based meta-learning techniques are both widely applicable and proficient at solving challenging few-shot learning and fast adaptation problems. However, they have practical difficulties when operating on high-dimensional parameter…

Machine Learning · Computer Science 2019-03-27 Andrei A. Rusu , Dushyant Rao , Jakub Sygnowski , Oriol Vinyals , Razvan Pascanu , Simon Osindero , Raia Hadsell

The behaviors and skills of models in many geosciences (e.g., hydrology and ecosystem sciences) strongly depend on spatially-varying parameters that need calibration. A well-calibrated model can reasonably propagate information from…

Machine Learning · Computer Science 2022-03-24 Wen-Ping Tsai , Dapeng Feng , Ming Pan , Hylke Beck , Kathryn Lawson , Yuan Yang , Jiangtao Liu , Chaopeng Shen

In-context learning (ICL) has shown impressive results in few-shot learning tasks, yet its underlying mechanism is still not fully understood. A recent line of work suggests that ICL performs gradient descent (GD)-based optimization…

Computation and Language · Computer Science 2024-04-02 Gilad Deutch , Nadav Magar , Tomer Bar Natan , Guy Dar

In this paper, we present a cross-entropy optimization method for hyperparameter optimization in stochastic gradient-based approaches to train deep neural networks. The value of a hyperparameter of a learning algorithm often has great…

Machine Learning · Computer Science 2024-09-17 Kevin Li , Fulu Li

Deep learning networks are typically trained by Stochastic Gradient Descent (SGD) methods that iteratively improve the model parameters by estimating a gradient on a very small fraction of the training data. A major roadblock faced when…

Machine Learning · Computer Science 2020-06-11 Tao Lin , Lingjing Kong , Sebastian U. Stich , Martin Jaggi