English
Related papers

Related papers: Regularized linear autoencoders recover the princi…

200 papers

In principle, applying variational autoencoders (VAEs) to sequential data offers a method for controlled sequence generation, manipulation, and structured representation learning. However, training sequence VAEs is challenging:…

Machine Learning · Computer Science 2022-12-19 Đorđe Miladinović , Kumar Shridhar , Kushal Jain , Max B. Paulus , Joachim M. Buhmann , Mrinmaya Sachan , Carl Allen

We study online learning in adversarial nonstationary environments. Since the future can be very different from the past, a critical challenge is to gracefully forget the history while new data comes in. To formalize this intuition, we…

Machine Learning · Computer Science 2024-06-21 Zhiyu Zhang , David Bombara , Heng Yang

Efficient training strategies for large-scale diffusion models have recently emphasized the importance of improving discriminative feature representations in these models. A central line of work in this direction is representation alignment…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Junno Yun , Yaşar Utku Alçalar , Mehmet Akçakaya

The choice of a proper learning rate is paramount for good Artificial Neural Network training and performance. In the past, one had to rely on experience and trial-and-error to find an adequate learning rate. Presently, a plethora of state…

Neural and Evolutionary Computing · Computer Science 2020-07-09 Pedro Carvalho , Nuno Lourenço , Filipe Assunção , Penousal Machado

The large capacity of neural networks enables them to learn complex functions. To avoid overfitting, networks however require a lot of training data that can be expensive and time-consuming to collect. A common practical approach to…

Machine Learning · Computer Science 2020-03-10 Majed El Helou , Frederike Dümbgen , Sabine Süsstrunk

We study the role of $L_2$ regularization in deep learning, and uncover simple relations between the performance of the model, the $L_2$ coefficient, the learning rate, and the number of training steps. These empirical relations hold when…

Machine Learning · Statistics 2021-01-05 Aitor Lewkowycz , Guy Gur-Ari

The cross-entropy loss commonly used in deep learning is closely related to the defining properties of optimal representations, but does not enforce some of the key properties. We show that this can be solved by adding a regularization…

Machine Learning · Statistics 2017-02-14 Alessandro Achille , Stefano Soatto

We consider the problem of training a deep neural network with nonsmooth regularization to retrieve a sparse and efficient sub-structure. Our regularizer is only assumed to be lower semi-continuous and prox-bounded. We combine an adaptive…

Machine Learning · Statistics 2022-06-20 Dounia Lakhmiri , Dominique Orban , Andrea Lodi

We present a general variational framework for the training of freeform nonlinearities in layered computational architectures subject to some slope constraints. The regularization that we add to the traditional training loss penalizes the…

Machine Learning · Statistics 2025-03-31 Michael Unser , Alexis Goujon , Stanislas Ducotterd

Modern machine learning models are often trained in a setting where the number of parameters exceeds the number of training samples. To understand the implicit bias of gradient descent in such overparameterized models, prior work has…

Machine Learning · Statistics 2025-10-29 Hannes Matt , Dominik Stöger

Autoencoders are a type of unsupervised neural networks, which can be used to solve various tasks, e.g., dimensionality reduction, image compression, and image denoising. An AE has two goals: (i) compress the original input to a…

Computer Vision and Pattern Recognition · Computer Science 2022-11-24 Firas Laakom , Jenni Raitoharju , Alexandros Iosifidis , Moncef Gabbouj

As one of the most popular generative models, Variational Autoencoder (VAE) approximates the posterior of latent variables based on amortized variational inference. However, when the decoder network is sufficiently expressive, VAE may lead…

Machine Learning · Computer Science 2021-10-26 Dazhong Shen , Chuan Qin , Chao Wang , Hengshu Zhu , Enhong Chen , Hui Xiong

We investigate the learning rate of multiple kernel leaning (MKL) with elastic-net regularization, which consists of an $\ell_1$-regularizer for inducing the sparsity and an $\ell_2$-regularizer for controlling the smoothness. We focus on a…

Machine Learning · Statistics 2011-07-14 Taiji Suzuki , Ryota Tomioka , Masashi Sugiyama

Parameter identification problems typically consist of a model equation, e.g. a (system of) ordinary or partial differential equation(s), and the observation equation. In the conventional reduced setting, the model equation is eliminated…

Numerical Analysis · Mathematics 2016-03-18 Barbara Kaltenbacher

The omnipresence of deep learning architectures such as deep convolutional neural networks (CNN)s is fueled by the synergistic combination of ever-increasing labeled datasets and specialized hardware. Despite the indisputable success, the…

Machine Learning · Statistics 2016-11-29 Meshia Cédric Oveneke , Mitchel Aliosha-Perez , Yong Zhao , Dongmei Jiang , Hichem Sahli

We propose a novel framework for learning stabilizable nonlinear dynamical systems for continuous control tasks in robotics. The key contribution is a control-theoretic regularizer for dynamics fitting rooted in the notion of…

Optimization and Control · Mathematics 2019-08-01 Sumeet Singh , Spencer M. Richards , Vikas Sindhwani , Jean-Jacques E. Slotine , Marco Pavone

We present a new approach for Neural Optimal Transport (NOT) training procedure, capable of accurately and efficiently estimating optimal transportation plan via specific regularization on dual Kantorovich potentials. The main bottleneck of…

Machine Learning · Computer Science 2024-10-21 Nazar Buzun , Maksim Bobrin , Dmitry V. Dylov

Learning meaningful representations using deep neural networks involves designing efficient training schemes and well-structured networks. Currently, the method of stochastic gradient descent that has a momentum with dropout is one of the…

Machine Learning · Computer Science 2016-01-15 Taehoon Lee , Minsuk Choi , Sungroh Yoon

Recent work suggests that convolutional neural networks of different architectures learn to classify images in the same order. To understand this phenomenon, we revisit the over-parametrized deep linear network model. Our analysis reveals…

Machine Learning · Computer Science 2023-12-29 Guy Hacohen , Daphna Weinshall

We investigate the statistical behavior of gradient descent iterates with dropout in the linear regression model. In particular, non-asymptotic bounds for the convergence of expectations and covariance matrices of the iterates are derived.…

Statistics Theory · Mathematics 2025-03-19 Gabriel Clara , Sophie Langer , Johannes Schmidt-Hieber