English
Related papers

Related papers: On the Theory of Implicit Deep Learning: Global Co…

200 papers

Implicit graph neural networks have gained popularity in recent years as they capture long-range dependencies while improving predictive performance in static graphs. Despite the tussle between performance degradation due to the…

Machine Learning · Computer Science 2024-06-27 Yongjian Zhong , Hieu Vu , Tianbao Yang , Bijaya Adhikari

In this paper, we present some theoretical work to explain why simple gradient descent methods are so successful in solving non-convex optimization problems in learning large-scale neural networks (NN). After introducing a mathematical tool…

Machine Learning · Computer Science 2023-05-01 Hui Jiang

Recent results in the literature suggest that the penultimate (second-to-last) layer representations of neural networks that are trained for classification exhibit a clustering property called neural collapse (NC). We study the implicit…

Machine Learning · Computer Science 2022-09-29 Tomer Galanti , Liane Galanti , Ido Ben-Shaul

Due to the non-convex nature of training Deep Neural Network (DNN) models, their effectiveness relies on the use of non-convex optimization heuristics. Traditional methods for training DNNs often require costly empirical methods to produce…

Machine Learning · Computer Science 2023-12-21 Tolga Ergen , Mert Pilanci

We propose an empirical approach centered on the spectral dynamics of weights -- the behavior of singular values and vectors during optimization -- to unify and clarify several phenomena in deep learning. We identify a consistent bias in…

Neural collapse is a highly symmetric geometric pattern of neural networks that emerges during the terminal phase of training, with profound implications on the generalization performance and robustness of the trained networks. To…

Machine Learning · Computer Science 2022-04-26 Wenlong Ji , Yiping Lu , Yiliang Zhang , Zhun Deng , Weijie J. Su

We study the fundamental optimization principles of self-attention, the defining mechanism of transformers, by analyzing the implicit bias of gradient-based optimizers in training a self-attention layer with a linear decoder in binary…

Machine Learning · Computer Science 2025-04-01 Bhavya Vasudeva , Puneesh Deora , Christos Thrampoulidis

Differentiable optimization layers are traditionally integrated in predict-then-optimize frameworks where a neural model estimates parameters that subsequently serve as fixed inputs to downstream decision-making optimization problems. In…

Machine Learning · Computer Science 2026-05-19 David Troxell , Noah Roemer , Guido Montúfar

This work attempts to interpret modern deep (convolutional) networks from the principles of rate reduction and (shift) invariant classification. We show that the basic iterative gradient ascent scheme for optimizing the rate reduction of…

Machine Learning · Computer Science 2020-10-30 Kwan Ho Ryan Chan , Yaodong Yu , Chong You , Haozhi Qi , John Wright , Yi Ma

We present a novel deep learning approach to approximate the solution of large, sparse, symmetric, positive-definite linear systems of equations. These systems arise from many problems in applied science, e.g., in numerical methods for…

Machine Learning · Computer Science 2022-10-04 Ayano Kaneda , Osman Akar , Jingyu Chen , Victoria Kala , David Hyde , Joseph Teran

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

Latent space models are effective tools for statistical modeling and exploration of network data. These models can effectively model real world network characteristics such as degree heterogeneity, transitivity, homophily, etc. Due to their…

Methodology · Statistics 2017-08-21 Zhuang Ma , Zongming Ma

Admittedly, Graph Convolution Network (GCN) has achieved excellent results on graph datasets such as social networks, citation networks, etc. However, softmax used as the decision layer in these frameworks is generally optimized with…

Machine Learning · Computer Science 2022-07-19 Xuelong Li , Ziheng Jiao , Hongyuan Zhang , Rui Zhang

We analyze the loss landscape and expressiveness of practical deep convolutional neural networks (CNNs) with shared weights and max pooling layers. We show that such CNNs produce linearly independent features at a "wide" layer which has…

Machine Learning · Computer Science 2018-06-07 Quynh Nguyen , Matthias Hein

Supervised training of neural networks for classification is typically performed with a global loss function. The loss function provides a gradient for the output layer, and this gradient is back-propagated to hidden layers to dictate an…

Machine Learning · Statistics 2019-05-09 Arild Nøkland , Lars Hiller Eidnes

This work investigates the use of smooth neural networks for modeling dynamic variations of implicit surfaces under the level set equation (LSE). For this, it extends the representation of neural implicit surfaces to the space-time…

Machine Learning · Computer Science 2024-04-15 Tiago Novello , Vinicius da Silva , Guilherme Schardong , Luiz Schirmer , Helio Lopes , Luiz Velho

Multi-layer neural networks are among the most powerful models in machine learning, yet the fundamental reasons for this success defy mathematical understanding. Learning a neural network requires to optimize a non-convex high-dimensional…

Machine Learning · Statistics 2022-06-08 Song Mei , Andrea Montanari , Phan-Minh Nguyen

We study regularized deep neural networks (DNNs) and introduce a convex analytic framework to characterize the structure of the hidden layers. We show that a set of optimal hidden layer weights for a norm regularized DNN training problem…

Machine Learning · Computer Science 2021-06-14 Tolga Ergen , Mert Pilanci

We consider networks, trained via stochastic gradient descent to minimize $\ell_2$ loss, with the training labels perturbed by independent noise at each iteration. We characterize the behavior of the training dynamics near any parameter…

Machine Learning · Computer Science 2020-07-23 Guy Blanc , Neha Gupta , Gregory Valiant , Paul Valiant

Differential equations are frequently used in engineering domains, such as modeling and control of industrial systems, where safety and performance guarantees are of paramount importance. Traditional physics-based modeling approaches…

Systems and Control · Electrical Eng. & Systems 2020-11-30 Aaron Tuor , Jan Drgona , Draguna Vrabie
‹ Prev 1 3 4 5 6 7 10 Next ›