English
Related papers

Related papers: Learning Optimal Linear Regularizers

200 papers

We consider a commonly studied supervised classification of a synthetic dataset whose labels are generated by feeding a one-layer neural network with random iid inputs. We study the generalization performances of standard classifiers in the…

Machine Learning · Statistics 2021-02-18 Benjamin Aubin , Florent Krzakala , Yue M. Lu , Lenka Zdeborová

This study investigates the problem of learning linear block codes optimized for Belief-Propagation decoders significantly improving performance compared to the state-of-the-art. Our previous research is extended with an enhanced system…

Signal Processing · Electrical Eng. & Systems 2025-10-02 Louis-Adrien Dufrène , Quentin Lampin , Guillaume Larue

The primary objective of learning methods is generalization. Classic uniform generalization bounds, which rely on VC-dimension or Rademacher complexity, fail to explain the significant attribute that over-parameterized models in deep…

Machine Learning · Computer Science 2025-03-07 Lijia Yu , Yibo Miao , Yifan Zhu , Xiao-Shan Gao , Lijun Zhang

We propose a new framework for reasoning about generalization in deep learning. The core idea is to couple the Real World, where optimizers take stochastic gradient steps on the empirical loss, to an Ideal World, where optimizers take steps…

Machine Learning · Computer Science 2021-02-22 Preetum Nakkiran , Behnam Neyshabur , Hanie Sedghi

Automating algorithm configuration is growing increasingly necessary as algorithms come with more and more tunable parameters. It is common to tune parameters using machine learning, optimizing performance metrics such as runtime and…

Artificial Intelligence · Computer Science 2020-12-25 Maria-Florina Balcan , Tuomas Sandholm , Ellen Vitercik

Regularization is a well studied problem in the context of neural networks. It is usually used to improve the generalization performance when the number of input samples is relatively small or heavily contaminated with noise. The…

Artificial Intelligence · Computer Science 2011-04-19 Salah Rifai , Xavier Glorot , Yoshua Bengio , Pascal Vincent

We learn recurrent neural network optimizers trained on simple synthetic functions by gradient descent. We show that these learned optimizers exhibit a remarkable degree of transfer in that they can be used to efficiently optimize a broad…

Overparametrized neural networks trained by gradient descent (GD) can provably overfit any training data. However, the generalization guarantee may not hold for noisy data. From a nonparametric perspective, this paper studies how well…

Machine Learning · Statistics 2021-09-28 Tianyang Hu , Wenjia Wang , Cong Lin , Guang Cheng

This work uses Push GP to automatically design both local and population-based optimisers for continuous-valued problems. The optimisers are trained on a single function optimisation landscape, using random transformations to discourage…

Neural and Evolutionary Computing · Computer Science 2021-05-31 Michael Lones

As application demands for online convex optimization accelerate, the need for designing new methods that simultaneously cover a large class of convex functions and impose the lowest possible regret is highly rising. Known online…

Machine Learning · Computer Science 2019-06-04 Saeed Masoudian , Ali Arabzadeh , Mahdi Jafari Siavoshani , Milad Jalal , Alireza Amouzad

Conventional wisdom in deep learning states that increasing depth improves expressiveness but complicates optimization. This paper suggests that, sometimes, increasing depth can speed up optimization. The effect of depth on optimization is…

Machine Learning · Computer Science 2018-06-12 Sanjeev Arora , Nadav Cohen , Elad Hazan

In this article, we improve extreme learning machines for regression tasks using a graph signal processing based regularization. We assume that the target signal for prediction or regression is a graph signal. With this assumption, we use…

Machine Learning · Statistics 2018-03-14 Arun Venkitaraman , Saikat Chatterjee , Peter Händel

When optimizing over-parameterized models, such as deep neural networks, a large set of parameters can achieve zero training error. In such cases, the choice of the optimization algorithm and its respective hyper-parameters introduces…

Machine Learning · Computer Science 2019-12-06 Gauthier Gidel , Francis Bach , Simon Lacoste-Julien

The ability to generalize to unseen domains is crucial for machine learning systems deployed in the real world, especially when we only have data from limited training domains. In this paper, we propose a simple and effective regularization…

Machine Learning · Computer Science 2023-12-06 Zhenmei Shi , Yifei Ming , Ying Fan , Frederic Sala , Yingyu Liang

We use convex relaxation techniques to provide a sequence of solutions to the matrix completion problem. Using the nuclear norm as a regularizer, we provide simple and very efficient algorithms for minimizing the reconstruction error…

Machine Learning · Statistics 2009-06-12 Rahul Mazumder , Trevor Hastie , Rob Tibshirani

Regularization is a powerful technique for extracting useful information from noisy data. Typically, it is implemented by adding some sort of norm constraint to an objective function and then exactly optimizing the modified objective…

Data Structures and Algorithms · Computer Science 2011-04-28 Michael W. Mahoney , Lorenzo Orecchia

The widely used nuclear norm heuristic for rank minimization problems introduces a regularization parameter which is difficult to tune. We have recently proposed a method to approximate the regularization path, i.e., the optimal solution as…

Systems and Control · Computer Science 2015-04-22 Niclas Blomberg , Cristian R. Rojas , Bo Wahlberg

Bilevel optimization and bilevel minimax optimization have recently emerged as unifying frameworks for a range of machine-learning tasks, including hyperparameter optimization and reinforcement learning. The existing literature focuses on…

Machine Learning · Computer Science 2026-04-23 Xuelin Zhang , Peipei Yuan

We consider the problem of learning a loss function which, when minimized over a training dataset, yields a model that approximately minimizes a validation error metric. Though learning an optimal loss function is NP-hard, we present an…

Machine Learning · Computer Science 2019-07-02 Matthew Streeter

Learning to optimize is a rapidly growing area that aims to solve optimization problems or improve existing optimization algorithms using machine learning (ML). In particular, the graph neural network (GNN) is considered a suitable ML model…

Machine Learning · Computer Science 2023-05-29 Ziang Chen , Jialin Liu , Xinshang Wang , Jianfeng Lu , Wotao Yin
‹ Prev 1 4 5 6 7 8 10 Next ›