English
Related papers

Related papers: Convex Relaxations of Convolutional Neural Nets

200 papers

A new computationally simple method of imposing hard convex constraints on the neural network output values is proposed. The key idea behind the method is to map a vector of hidden parameters of the network to a point that is guaranteed to…

Machine Learning · Computer Science 2023-07-21 Andrei V. Konstantinov , Lev V. Utkin

In this paper, we propose an unifying view of several recently proposed structured sparsity-inducing norms. We consider the situation of a model simultaneously (a) penalized by a set- function de ned on the support of the unknown parameter…

Machine Learning · Statistics 2012-05-08 Guillaume Obozinski , Francis Bach

This paper studies hidden convexity properties associated with constrained optimization problems over the set of rotation matrices $\text{SO}(n)$. Such problems are nonconvex due to the constraint $X \in \text{SO}(n)$. Nonetheless, we show…

Optimization and Control · Mathematics 2024-05-01 Akshay Ramachandran , Kevin Shu , Alex L. Wang

We study model recovery for data classification, where the training labels are generated from a one-hidden-layer neural network with sigmoid activations, also known as a single-layer feedforward network, and the goal is to recover the…

Machine Learning · Statistics 2020-05-07 Haoyu Fu , Yuejie Chi , Yingbin Liang

Recovering a low-rank tensor from incomplete information is a recurring problem in signal processing and machine learning. The most popular convex relaxation of this problem minimizes the sum of the nuclear norms of the unfoldings of the…

Machine Learning · Statistics 2013-08-16 Cun Mu , Bo Huang , John Wright , Donald Goldfarb

Compressing neural nets is an active research problem, given the large size of state-of-the-art nets for tasks such as object recognition, and the computational limits imposed by mobile devices. We give a general formulation of model…

Machine Learning · Computer Science 2017-07-06 Miguel Á. Carreira-Perpiñán

We present a new approach to learning the structure and parameters of a Bayesian network based on regularized estimation in an exponential family representation. Here we show that, given a fixed variable order, the optimal structure and…

Machine Learning · Computer Science 2012-07-02 Yuhong Guo , Dale Schuurmans

In this paper, we introduce methods from convex optimization to solve the multimarginal transport type problems arise in the context of density functional theory. Convex relaxations are used to provide outer approximation to the set of…

Optimization and Control · Mathematics 2018-08-15 Yuehaw Khoo , Lexing Ying

We give the first provably efficient algorithm for learning a one hidden layer convolutional network with respect to a general class of (potentially overlapping) patches. Additionally, our algorithm requires only mild conditions on the…

Machine Learning · Computer Science 2018-02-08 Surbhi Goel , Adam Klivans , Raghu Meka

The softmax function is a ubiquitous component at the output of neural networks and increasingly in intermediate layers as well. This paper provides convex lower bounds and concave upper bounds on the softmax function, which are compatible…

Machine Learning · Computer Science 2023-03-06 Dennis Wei , Haoze Wu , Min Wu , Pin-Yu Chen , Clark Barrett , Eitan Farchi

Equivariant neural networks exploit underlying task symmetries to improve generalization, but strict equivariance constraints can induce more complex optimization dynamics that can hinder learning. Prior work addresses these limitations by…

Machine Learning · Computer Science 2026-02-24 Stefanos Pertigkiozoglou , Mircea Petrache , Shubhendu Trivedi , Kostas Daniilidis

Several convex relaxations of the optimal power flow (OPF) problem have recently been developed using both bus injection models and branch flow models. In this paper, we prove relations among three convex relaxations: a semidefinite…

Systems and Control · Computer Science 2014-01-10 Subhonmesh Bose , Steven H. Low , Thanchanok Teeraratkul , Babak Hassibi

We study the loss surface of DNNs with $L_{2}$ regularization. We show that the loss in terms of the parameters can be reformulated into a loss in terms of the layerwise activations $Z_{\ell}$ of the training set. This reformulation reveals…

Machine Learning · Statistics 2022-10-17 Arthur Jacot , Eugene Golikov , Clément Hongler , Franck Gabriel

Deep neural networks (DNNs) have achieved significant success in a variety of real world applications, i.e., image classification. However, tons of parameters in the networks restrict the efficiency of neural networks due to the large model…

Machine Learning · Computer Science 2019-08-21 Yuzhe Ma , Ran Chen , Wei Li , Fanhua Shang , Wenjian Yu , Minsik Cho , Bei Yu

Single layer feedforward networks with random weights are known for their non-iterative and fast training algorithms and are successful in a variety of classification and regression problems. A major drawback of these networks is that they…

Machine Learning · Computer Science 2020-09-25 Ajay M. Patrikar

In this paper, we study the dynamics of gradient descent in learning neural networks for classification problems. Unlike in existing works, we consider the linearly non-separable case where the training data of different classes lie in…

Machine Learning · Computer Science 2020-12-11 Ziang Long , Penghang Yin , Jack Xin

We present a simple linear regression based approach for learning the weights and biases of a neural network, as an alternative to standard gradient based backpropagation. The present work is exploratory in nature, and we restrict the…

Machine Learning · Computer Science 2023-07-17 Harshad Khadilkar

In this article, we introduce a novel normalization technique for neural network weight matrices, which we term weight conditioning. This approach aims to narrow the gap between the smallest and largest singular values of the weight…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Hemanth Saratchandran , Thomas X. Wang , Simon Lucey

The goal of this paper is to survey the properties of the eigenvalue relaxation for least squares binary problems. This relaxation is a convex program which is obtained as the Lagrangian dual of the original problem with an implicit compact…

Methodology · Statistics 2009-02-10 Stephane Chretien , Franck Corset

The integration of algorithmic components into neural architectures has gained increased attention recently, as it allows training neural networks with new forms of supervision such as ordering constraints or silhouettes instead of using…

Machine Learning · Computer Science 2021-10-27 Felix Petersen , Christian Borgelt , Hilde Kuehne , Oliver Deussen