English
Related papers

Related papers: Learning time-scales in two-layers neural networks

200 papers

The generalization mystery of overparametrized deep nets has motivated efforts to understand how gradient descent (GD) converges to low-loss solutions that generalize well. Real-life neural networks are initialized from small random values…

Machine Learning · Computer Science 2021-11-10 Kaifeng Lyu , Zhiyuan Li , Runzhe Wang , Sanjeev Arora

Reinforcement learning has been successful across several applications in which agents have to learn to act in environments with sparse feedback. However, despite this empirical success there is still a lack of theoretical understanding of…

Machine Learning · Statistics 2023-11-08 Blake Bordelon , Paul Masset , Henry Kuo , Cengiz Pehlevan

One of the central questions in the theory of deep learning is to understand how neural networks learn hierarchical features. The ability of deep networks to extract salient features is crucial to both their outstanding generalization…

Machine Learning · Computer Science 2025-04-03 Eshaan Nichani , Alex Damian , Jason D. Lee

Generative Flow Networks (GFlowNets) have emerged as a powerful paradigm for generating composite structures, demonstrating considerable promise across diverse applications. While substantial progress has been made in exploring their…

Machine Learning · Computer Science 2025-05-06 Tianshu Yu

Understanding the implicit bias of training algorithms is of crucial importance in order to explain the success of overparametrised neural networks. In this paper, we study the dynamics of stochastic gradient descent over diagonal linear…

Machine Learning · Computer Science 2021-12-08 Scott Pesme , Loucas Pillaud-Vivien , Nicolas Flammarion

Neural networks trained with gradient descent can undergo non-trivial phase transitions as a function of the learning rate. In \cite{lewkowycz2020large} it was discovered that wide neural nets can exhibit a catapult phase for super-critical…

Machine Learning · Computer Science 2025-09-26 David Meltzer , Min Chen , Junyu Liu

Recently, a spate of papers have provided positive theoretical results for training over-parameterized neural networks (where the network size is larger than what is needed to achieve low error). The key insight is that with sufficient…

Machine Learning · Computer Science 2022-03-01 Gilad Yehudai , Ohad Shamir

In supervised learning, it is known that overparameterized neural networks with one hidden layer provably and efficiently learn and generalize, when trained using stochastic gradient descent with a sufficiently small learning rate and…

Machine Learning · Computer Science 2022-03-24 Kulin Shah , Amit Deshpande , Navin Goyal

We consider dynamical and geometrical aspects of deep learning. For many standard choices of layer maps we display semi-invariant metrics which quantify differences between data or decision functions. This allows us, when considering random…

Machine Learning · Computer Science 2021-04-23 Benny Avelin , Anders Karlsson

We introduce generative models for accelerating simulations of complex systems through learning and evolving their effective dynamics. In the proposed Generative Learning of Effective Dynamics (G-LED), instances of high dimensional data are…

Machine Learning · Computer Science 2024-02-28 Han Gao , Sebastian Kaltenbach , Petros Koumoutsakos

To understand feature learning dynamics in neural networks, recent theoretical works have focused on gradient-based learning of Gaussian single-index models, where the label is a nonlinear function of a latent one-dimensional projection of…

Machine Learning · Computer Science 2025-10-27 Konstantinos Christopher Tsiolis , Alireza Mousavi-Hosseini , Murat A. Erdogdu

Dynamic neural network is an emerging research topic in deep learning. Compared to static models which have fixed computational graphs and parameters at the inference stage, dynamic networks can adapt their structures or parameters to…

Computer Vision and Pattern Recognition · Computer Science 2021-12-03 Yizeng Han , Gao Huang , Shiji Song , Le Yang , Honghui Wang , Yulin Wang

With the rise of big data analytics, multi-layer neural networks have surfaced as one of the most powerful machine learning methods. However, their theoretical mathematical properties are still not fully understood. Training a neural…

Machine Learning · Computer Science 2021-01-01 Victor Luo , Yazhen Wang , Glenn Fung

Generative flow networks (GFlowNets) are a family of algorithms that learn a generative policy to sample discrete objects $x$ with non-negative reward $R(x)$. Learning objectives guarantee the GFlowNet samples $x$ from the target…

Machine Learning · Computer Science 2023-05-15 Max W. Shen , Emmanuel Bengio , Ehsan Hajiramezanali , Andreas Loukas , Kyunghyun Cho , Tommaso Biancalani

Recursive Neural Networks are non-linear adaptive models that are able to learn deep structured information. However, these models have not yet been broadly accepted. This fact is mainly due to its inherent complexity. In particular, not…

Neural and Evolutionary Computing · Computer Science 2009-11-18 Alejandro Chinea

Nowadays, neural networks are widely used in many applications as artificial intelligence models for learning tasks. Since typically neural networks process a very large amount of data, it is convenient to formulate them within the…

Optimization and Control · Mathematics 2021-11-10 M. Herty , T. Trimborn , G. Visconti

A common problem of classical neural network architectures is that additional information or expert knowledge cannot be naturally integrated into the learning process. To overcome this limitation, we propose a two-step approach consisting…

Machine Learning · Computer Science 2024-06-17 Florian Seiffarth

Recurrent neural networks (RNNs) trained on low-dimensional tasks have been widely used to model functional biological networks. However, the solutions found by learning and the effect of initial connectivity are not well understood. Here,…

Neurons and Cognition · Quantitative Biology 2021-05-17 Friedrich Schuessler , Francesca Mastrogiuseppe , Alexis Dubreuil , Srdjan Ostojic , Omri Barak

Many types of data from fields including natural language processing, computer vision, and bioinformatics, are well represented by discrete, compositional structures such as trees, sequences, or matchings. Latent structure models are a…

Machine Learning · Computer Science 2026-02-04 Vlad Niculae , Caio F. Corro , Nikita Nangia , Tsvetomila Mihaylova , André F. T. Martins

Recurrent Neural Networks (RNNs) achieve state-of-the-art results in many sequence-to-sequence modeling tasks. However, RNNs are difficult to train and tend to suffer from overfitting. Motivated by the Data Processing Inequality (DPI), we…

Machine Learning · Statistics 2018-05-24 Ziv Aharoni , Gal Rattner , Haim Permuter