English
Related papers

Related papers: KKT-based optimality conditions for neural network…

200 papers

Quantum state tomography (QST) aiming at reconstructing the density matrix of a quantum state plays an important role in various emerging quantum technologies. Recognizing the challenges posed by imperfect measurement data, we develop a…

Quantum Physics · Physics 2025-03-31 Hailan Ma , Daoyi Dong , Ian R. Petersen , Chang-Jiang Huang , Guo-Yong Xiang

In this paper, we propose an inexact proximal Newton-type method for nonconvex composite problems. We establish the global convergence rate of the order $\mathcal{O}(k^{-1/2})$ in terms of the minimal norm of the KKT residual mapping and…

Optimization and Control · Mathematics 2024-12-26 Hong Zhu

We propose a non-stationary iterated network Tikhonov (iNETT) method for the solution of ill-posed inverse problems. The iNETT employs deep neural networks to build a data-driven regularizer, and it avoids the difficult task of estimating…

Numerical Analysis · Mathematics 2023-04-05 Davide Bianchi , Guanghao Lai , Wenbin Li

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

The accuracy and complexity of machine learning algorithms based on kernel optimization are limited by the set of kernels over which they are able to optimize. An ideal set of kernels should: admit a linear parameterization (for…

Machine Learning · Computer Science 2020-06-16 Brendon K. Colbert , Matthew M. Peet

Training data reconstruction from KKT conditions has shown striking empirical success, yet it remains unclear when the resulting KKT equations have unique solutions and, even in identifiable regimes, how to reliably recover solutions by…

Machine Learning · Computer Science 2026-02-10 Yujie Shen , Zihan Wang , Jian Qian , Qi Lei

Distribution network reconfiguration (DNR) is an effective approach for optimizing distribution network operation. However, the DNR problem is computationally challenging due to the mixed-integer non-convex nature. One feasible approach for…

Optimization and Control · Mathematics 2025-05-13 Rong-Peng Liu , Yue Song , Xiaozhe Wang , Bo Zeng

In this paper we develop a higher-order method for solving composite (non)convex minimization problems with smooth (non)convex functional constraints. At each iteration our method approximates the smooth part of the objective function and…

Optimization and Control · Mathematics 2025-03-04 Yassine Nabou , Ion Necoara

The problem of selecting optimal backdoor adjustment sets to estimate causal effects in graphical models with hidden and conditioned variables is addressed. Previous work has defined optimality as achieving the smallest asymptotic…

Machine Learning · Computer Science 2023-06-26 Jakob Runge

A recent line of work has shown that an overparametrized neural network can perfectly fit the training data, an otherwise often intractable nonconvex optimization problem. For (fully-connected) shallow networks, in the best case scenario,…

Machine Learning · Computer Science 2019-10-30 Armin Eftekhari , ChaeHwan Song , Volkan Cevher

We consider variants of trust-region and cubic regularization methods for non-convex optimization, in which the Hessian matrix is approximated. Under mild conditions on the inexact Hessian, and using approximate solution of the…

Optimization and Control · Mathematics 2019-05-15 Peng Xu , Fred Roosta , Michael W. Mahoney

We consider optimizing two-layer neural networks in the mean-field regime where the learning dynamics of network weights can be approximated by the evolution in the space of probability measures over the weight parameters associated with…

Machine Learning · Computer Science 2022-10-19 Jingwei Zhang , Xunpeng Huang , Jincheng Yu

We study stochastic optimization of nonconvex loss functions, which are typical objectives for training neural networks. We propose stochastic approximation algorithms which optimize a series of regularized, nonlinearized losses on large…

Machine Learning · Computer Science 2019-03-12 Weiran Wang , Nathan Srebro

Gate-based quantum computations represent an essential to realize near-term quantum computer architectures. A gate-model quantum neural network (QNN) is a QNN implemented on a gate-model quantum computer, realized via a set of unitaries…

Quantum Physics · Physics 2019-09-04 Laszlo Gyongyosi , Sandor Imre

Hidden convex optimization is such a class of nonconvex optimization problems that can be globally solved in polynomial time via equivalent convex programming reformulations. In this paper, we focus on checking local optimality in hidden…

Optimization and Control · Mathematics 2021-09-08 Mengmeng Song , Yong Xia , Hongying Liu

The deep neural network suffers from many fundamental issues in machine learning. For example, it often gets trapped into a local minimum in training, and its prediction uncertainty is hard to be assessed. To address these issues, we…

Machine Learning · Statistics 2022-01-17 Yan Sun , Faming Liang

At its core, machine learning seeks to train models that reliably generalize beyond noisy observations; however, the theoretical vacuum in which state-of-the-art universal approximation theorems (UATs) operate isolates them from this goal,…

Machine Learning · Statistics 2025-09-03 Anastasis Kratsios , Tin Sum Cheng , Daniel Roy

The principle of adaptation in a noisy retrieval environment is extended here to a diluted attractor neural network of Q-state neurons trained with noisy data. The network is adapted to an appropriate noisy training overlap and training…

Disordered Systems and Neural Networks · Physics 2009-10-31 R. Erichsen , W. K. Theumann

Training neural networks involves solving large-scale non-convex optimization problems. This task has long been believed to be extremely difficult, with fear of local minima and other obstacles motivating a variety of schemes to improve…

Neural and Evolutionary Computing · Computer Science 2015-05-25 Ian J. Goodfellow , Oriol Vinyals , Andrew M. Saxe

The successful training of deep neural networks requires addressing challenges such as overfitting, numerical instabilities leading to divergence, and increasing variance in the residual stream. A common solution is to apply regularization…

Machine Learning · Computer Science 2025-11-20 Jörg K. H. Franke , Urs Spiegelhalter , Marianna Nezhurina , Jenia Jitsev , Frank Hutter , Michael Hefenbrock
‹ Prev 1 3 4 5 6 7 10 Next ›