English
Related papers

Related papers: A Closer Look at Double Backpropagation

200 papers

Despite a great deal of research, it is still unclear why neural networks are so susceptible to adversarial examples. In this work, we identify natural settings where depth-$2$ ReLU networks trained with gradient flow are provably…

Machine Learning · Computer Science 2022-10-05 Gal Vardi , Gilad Yehudai , Ohad Shamir

The backpropagation algorithm for neural networks is widely felt hard to understand, despite the existence of some well-written explanations and/or derivations. This paper provides a new derivation of this algorithm based on the concept of…

Machine Learning · Computer Science 2022-05-03 Yiping Cheng

With the unprecedented growth of signal processing and machine learning application domains, there has been a tremendous expansion of interest in distributed optimization methods to cope with the underlying large-scale problems.…

Optimization and Control · Mathematics 2022-10-25 Hansi Abeynanda , Chathuranga Weeraddana , G. H. J. Lanel , Carlo Fischione

Neural networks are complex functions of both their inputs and parameters. Much prior work in deep learning theory analyzes the distribution of network outputs at a fixed a set of inputs (e.g. a training dataset) over random initializations…

Disordered Systems and Neural Networks · Physics 2025-04-08 Mike Winer , Boris Hanin

Overparameterized ML models, including neural networks, typically induce underdetermined training objectives with multiple global minima. The implicit bias refers to the limiting global minimum that is attained by a common optimization…

Machine Learning · Statistics 2026-03-06 Kuo-Wei Lai , Guanghui Wang , Molei Tao , Vidya Muthukumar

Recently, neural networks in machine learning use rectified linear units (ReLUs) in early processing layers for better performance. Training these structures sometimes results in "dying ReLU units" with near-zero outputs. We first explore…

Machine Learning · Computer Science 2018-12-17 Scott C. Douglas , Jiutian Yu

Fractional gradient descent has been studied extensively, with a focus on its ability to extend traditional gradient descent methods by incorporating fractional-order derivatives. This approach allows for more flexibility in navigating…

Machine Learning · Computer Science 2024-11-25 Teodor Alexandru Szente , James Harrison , Mihai Zanfir , Cristian Sminchisescu

The success of deep neural networks hinges on our ability to accurately and efficiently optimize high-dimensional, non-convex functions. In this paper, we empirically investigate the loss functions of state-of-the-art networks, and how…

Machine Learning · Computer Science 2017-12-11 Daniel Jiwoong Im , Michael Tao , Kristin Branson

Neuron death is a complex phenomenon with implications for model trainability: the deeper the network, the lower the probability of finding a valid initialization. In this work, we derive both upper and lower bounds on the probability that…

Machine Learning · Computer Science 2021-06-14 Blaine Rister , Daniel L. Rubin

Natural gradient descent has proven effective at mitigating the effects of pathological curvature in neural network optimization, but little is known theoretically about its convergence properties, especially for \emph{nonlinear} networks.…

Machine Learning · Statistics 2019-10-29 Guodong Zhang , James Martens , Roger Grosse

To optimize a neural network one often thinks of optimizing its parameters, but it is ultimately a matter of optimizing the function that maps inputs to outputs. Since a change in the parameters might serve as a poor proxy for the change in…

Neural and Evolutionary Computing · Computer Science 2019-06-28 Ari S. Benjamin , David Rolnick , Konrad Kording

A wide array of image recovery problems can be abstracted into the problem of minimizing a sum of composite convex functions in a Hilbert space. To solve such problems, primal-dual proximal approaches have been developed which provide…

Optimization and Control · Mathematics 2014-06-23 Patrick L. Combettes , Laurent Condat , Jean-Christophe Pesquet , Bang Cong Vu

A class of linear parabolic equations are considered. We derive a common framework for the a posteriori error analysis of certain second-order time discretisations combined with finite element discretisations in space. In particular we…

Numerical Analysis · Mathematics 2023-04-05 Torsten Linß , Martin Ossadnik , Goran Radojev

We consider nonlinear optimization problems that involve surrogate models represented by neural networks. We demonstrate first how to directly embed neural network evaluation into optimization models, highlight a difficulty with this…

Optimization and Control · Mathematics 2021-11-23 Dominic Yang , Prasanna Balaprakash , Sven Leyffer

Modern deep-learning systems are specialized to problem settings in which training occurs once and then never again, as opposed to continual-learning settings in which training occurs continually. If deep-learning systems are applied in a…

Machine Learning · Computer Science 2024-04-11 Shibhansh Dohare , J. Fernando Hernandez-Garcia , Parash Rahman , A. Rupam Mahmood , Richard S. Sutton

There is a growing attention given to utilizing Lagrangian and Hamiltonian mechanics with network training in order to incorporate physics into the network. Most commonly, conservative systems are modeled, in which there are no frictional…

Machine Learning · Computer Science 2024-05-28 Veera Sundararaghavan , Megna N. Shah , Jeff P. Simmons

The binary neural network, largely saving the storage and computation, serves as a promising technique for deploying deep models on resource-limited devices. However, the binarization inevitably causes severe information loss, and even…

Neural and Evolutionary Computing · Computer Science 2020-04-08 Haotong Qin , Ruihao Gong , Xianglong Liu , Xiao Bai , Jingkuan Song , Nicu Sebe

In this paper, training a neural network is identified, exactly, as a search through Hamilton--Jacobi initial-value problems: each gradient step selects the initial data of a viscous Hamilton--Jacobi equation whose Hopf--Cole propagator…

Machine Learning · Computer Science 2026-05-29 Jose Marie Antonio Miñoza , Erika Fille T. Legara , Christopher P. Monterola

Hebbian plasticity is a powerful principle that allows biological brains to learn from their lifetime experience. By contrast, artificial neural networks trained with backpropagation generally have fixed connection weights that do not…

Neural and Evolutionary Computing · Computer Science 2016-10-20 Thomas Miconi

In a physical neural system, where storage and processing are intimately intertwined, the rules for adjusting the synaptic weights can only depend on variables that are available locally, such as the activity of the pre- and post-synaptic…

Machine Learning · Computer Science 2016-10-25 Pierre Baldi , Peter Sadowski