English
Related papers

Related papers: Expected Gradients of Maxout Networks and Conseque…

200 papers

Stochastic gradient methods are central to large-scale learning, yet their generalization theory typically relies on independent sampling assumptions. In many practical applications, data are generated by Markov chains and learning is…

Machine Learning · Computer Science 2026-05-05 Jiahuan Wang , Ziqing Wen , Ping Luo , Dongsheng Li , Tao Sun

We study a variation of vanilla stochastic gradient descent where the optimizer only has access to a Markovian sampling scheme. These schemes encompass applications that range from decentralized optimization with a random walker (token…

Optimization and Control · Mathematics 2023-06-26 Mathieu Even

Given any deep fully connected neural network, initialized with random Gaussian parameters, we bound from above the quadratic Wasserstein distance between its output distribution and a suitable Gaussian process. Our explicit inequalities…

Machine Learning · Computer Science 2023-09-25 Andrea Basteri , Dario Trevisan

We investigate how the final parameters found by stochastic gradient descent are influenced by over-parameterization. We generate families of models by increasing the number of channels in a base network, and then perform a large…

Machine Learning · Computer Science 2019-05-10 Daniel S. Park , Jascha Sohl-Dickstein , Quoc V. Le , Samuel L. Smith

The capacity of neural networks like the widely adopted transformer is known to be very high. Evidence is emerging that they learn successfully due to inductive bias in the training routine, typically a variant of gradient descent (GD). To…

Machine Learning · Computer Science 2023-03-09 William Merrill , Vivek Ramanujan , Yoav Goldberg , Roy Schwartz , Noah Smith

Variational quantum circuits have been widely employed in quantum simulation and quantum machine learning in recent years. However, quantum circuits with random structures have poor trainability due to the exponentially vanishing gradient…

Quantum Physics · Physics 2025-02-20 Kaining Zhang , Liu Liu , Min-Hsiu Hsieh , Dacheng Tao

This paper studies how neural network architecture affects the speed of training. We introduce a simple concept called gradient confusion to help formally analyze this. When gradient confusion is high, stochastic gradients produced by…

Machine Learning · Computer Science 2020-07-08 Karthik A. Sankararaman , Soham De , Zheng Xu , W. Ronny Huang , Tom Goldstein

Generalization error bounds for deep neural networks trained by stochastic gradient descent (SGD) are derived by combining a dynamical control of an appropriate parameter norm and the Rademacher complexity estimate based on parameter norms.…

Machine Learning · Computer Science 2023-05-30 Mingze Wang , Chao Ma

The algorithms used to train neural networks, like stochastic gradient descent (SGD), have close parallels to natural processes that navigate a high-dimensional parameter space -- for example protein folding or evolution. Our study uses a…

Machine Learning · Computer Science 2023-06-07 Shishir Adhikari , Alkan Kabakçıoğlu , Alexander Strang , Deniz Yuret , Michael Hinczewski

We propose a guided dropout regularizer for deep networks based on the evidence of a network prediction defined as the firing of neurons in specific paths. In this work, we utilize the evidence at each neuron to determine the probability of…

Computer Vision and Pattern Recognition · Computer Science 2021-01-22 Andrea Zunino , Sarah Adel Bargal , Pietro Morerio , Jianming Zhang , Stan Sclaroff , Vittorio Murino

Upper bounds are derived on the total variation distance between the invariant distributions of two stochastic matrices differing on a subset W of rows. Such bounds depend on three parameters: the mixing time and the minimal expected…

Probability · Mathematics 2015-05-19 Giacomo Como , Fabio Fagnani

We propose a numerical method to learn Maximum Entropy (MaxEnt) distributions with spatio-temporal constraints from experimental spike trains. This is an extension of two papers [10] and [4] who proposed the estimation of parameters where…

Neurons and Cognition · Quantitative Biology 2015-06-19 Hassan Nasser , Bruno Cessac

Gradient-based methods successfully train highly overparameterized models in practice, even though the associated optimization problems are markedly nonconvex. Understanding the mechanisms that make such methods effective has become a…

Machine Learning · Computer Science 2026-01-21 Hippolyte Labarrière , Cesare Molinari , Lorenzo Rosasco , Cristian Vega , Silvia Villa

Many modern learning tasks involve fitting nonlinear models to data which are trained in an overparameterized regime where the parameters of the model exceed the size of the training dataset. Due to this overparameterization, the training…

Machine Learning · Computer Science 2018-12-27 Samet Oymak , Mahdi Soltanolkotabi

We study the optimal control of the mean and variance of the network state vector. We develop an algorithm that uses projected gradient descent to optimize the control input placement, subject to constraints on the state that must be…

Optimization and Control · Mathematics 2024-04-16 Philip Solimine , Anke Meyer-Baese

While significant theoretical progress has been achieved, unveiling the generalization mystery of overparameterized neural networks still remains largely elusive. In this paper, we study the generalization behavior of shallow neural…

Machine Learning · Computer Science 2022-09-21 Yunwen Lei , Rong Jin , Yiming Ying

The recent theoretical analysis of deep neural networks in their infinite-width limits has deepened our understanding of initialisation, feature learning, and training of those networks, and brought new practical techniques for finding…

Machine Learning · Computer Science 2024-08-23 Taeyoung Kim , Hongseok Yang

In this paper, we propose and study random maxout features, which are constructed by first projecting the input data onto sets of randomly generated vectors with Gaussian elements, and then outputing the maximum projection value for each…

Machine Learning · Computer Science 2015-06-15 Youssef Mroueh , Steven Rennie , Vaibhava Goel

We consider the problem of designing models to leverage a recently introduced approximate model averaging technique called dropout. We define a simple new model called maxout (so named because its output is the max of a set of inputs, and…

Machine Learning · Statistics 2013-09-23 Ian J. Goodfellow , David Warde-Farley , Mehdi Mirza , Aaron Courville , Yoshua Bengio

The edge-of-chaos dynamics of wide randomly initialized low-rank feedforward networks are analyzed. Formulae for the optimal weight and bias variances are extended from the full-rank to low-rank setting and are shown to follow from…

Machine Learning · Statistics 2023-02-01 Thiziri Nait Saada , Jared Tanner