English
Related papers

Related papers: Deep Learning without Global Optimization by Rando…

200 papers

Activation functions are crucial for deep neural networks. This novel work frames the problem of training neural network with learnable polynomial activation functions as a polynomial optimization problem, which is solvable by the…

Optimization and Control · Mathematics 2025-10-07 Linghao Zhang , Jiawang Nie , Tingting Tang

Restricted Boltzmann Machines and Deep Belief Networks have been successfully used in a wide variety of applications including image classification and speech recognition. Inference and learning in these algorithms uses a Markov Chain Monte…

We show the existence of a deep neural network capable of approximating a wide class of high-dimensional approximations. The construction of the proposed neural network is based on a quasi-optimal polynomial approximation. We show that this…

Numerical Analysis · Mathematics 2019-12-09 Joseph Daws , Clayton Webster

We study deep neural networks and their use in semiparametric inference. We establish novel rates of convergence for deep feedforward neural nets. Our new rates are sufficiently fast (in some cases minimax optimal) to allow us to establish…

Econometrics · Economics 2021-01-20 Max H. Farrell , Tengyuan Liang , Sanjog Misra

In the current research of neural networks, the activation function is manually specified by human and not able to change themselves during training. This paper focus on how to make the activation function trainable for deep neural…

Computer Vision and Pattern Recognition · Computer Science 2020-06-08 Zhaohe Liao

We study the training process of Deep Neural Networks (DNNs) from the Fourier analysis perspective. We demonstrate a very universal Frequency Principle (F-Principle) -- DNNs often fit target functions from low to high frequencies -- on…

Machine Learning · Computer Science 2024-05-24 Zhi-Qin John Xu , Yaoyu Zhang , Tao Luo , Yanyang Xiao , Zheng Ma

Artificial neural networks typically have a fixed, non-linear activation function at each neuron. We have designed a novel form of piecewise linear activation function that is learned independently for each neuron using gradient descent.…

Neural and Evolutionary Computing · Computer Science 2015-04-22 Forest Agostinelli , Matthew Hoffman , Peter Sadowski , Pierre Baldi

Monte Carlo methods are widely used in particle physics to integrate and sample probability distributions (differential cross sections or decay rates) on multi-dimensional phase spaces. We present a Neural Network (NN) algorithm optimized…

High Energy Physics - Phenomenology · Physics 2020-10-21 Matthew D. Klimek , Maxim Perelstein

We present a non-convex optimization algorithm metaheuristic, based on the training of a deep generative network, which enables effective searching within continuous, ultra-high dimensional landscapes. During network training, populations…

Machine Learning · Computer Science 2023-07-11 Jiaqi Jiang , Jonathan A. Fan

Bayesian inference in deep neural networks is challenging due to the high-dimensional, strongly multi-modal parameter posterior density landscape. Markov chain Monte Carlo approaches asymptotically recover the true posterior but are…

We explore the phase diagram of approximation rates for deep neural networks and prove several new theoretical results. In particular, we generalize the existing result on the existence of deep discontinuous phase in ReLU networks to…

Neural and Evolutionary Computing · Computer Science 2021-01-07 Dmitry Yarotsky , Anton Zhevnerchuk

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

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

Multilayer switch networks are proposed as artificial generators of high-dimensional discrete data (e.g., binary vectors, categorical data, natural language, network log files, and discrete-valued time series). Unlike deconvolution networks…

Machine Learning · Computer Science 2019-03-15 Payam Delgosha , Naveen Goela

Deep reinforcement learning (RL) agents often fail to generalize to unseen environments (yet semantically similar to trained agents), particularly when they are trained on high-dimensional state spaces, such as images. In this paper, we…

Machine Learning · Computer Science 2020-02-18 Kimin Lee , Kibok Lee , Jinwoo Shin , Honglak Lee

Artificial Neural Networks were recently shown to be an efficient representation of highly-entangled many-body quantum states. In practical applications, neural-network states inherit numerical schemes used in Variational Monte Carlo, most…

Disordered Systems and Neural Networks · Physics 2020-01-22 Or Sharir , Yoav Levine , Noam Wies , Giuseppe Carleo , Amnon Shashua

We develop a probabilistic framework for deep learning based on the Deep Rendering Mixture Model (DRMM), a new generative probabilistic model that explicitly capture variations in data due to latent task nuisance variables. We demonstrate…

Machine Learning · Statistics 2016-12-07 Ankit B. Patel , Tan Nguyen , Richard G. Baraniuk

We present a scalable and effective exploration strategy based on Thompson sampling for reinforcement learning (RL). One of the key shortcomings of existing Thompson sampling algorithms is the need to perform a Gaussian approximation of the…

Machine Learning · Computer Science 2024-03-19 Haque Ishfaq , Qingfeng Lan , Pan Xu , A. Rupam Mahmood , Doina Precup , Anima Anandkumar , Kamyar Azizzadenesheli

Restricted Boltzmann Machines and Deep Belief Networks have been successfully used in probabilistic generative model applications such as image occlusion removal, pattern completion and motion synthesis. Generative inference in such…

Neural and Evolutionary Computing · Computer Science 2016-02-22 Ojash Neopane , Srinjoy Das , Ery Arias-Castro , Kenneth Kreutz-Delgado

We present a geometrically enhanced Markov chain Monte Carlo sampler for networks based on a discrete curvature measure defined on graphs. Specifically, we incorporate the concept of graph Forman curvature into sampling procedures on both…

Machine Learning · Statistics 2021-10-12 John Sigbeku , Emil Saucan , Anthea Monod