English
Related papers

Related papers: The Implicit Bias of Adam on Separable Data

200 papers

Most modern learning problems are over-parameterized, where the number of learnable parameters is much greater than the number of training data points. In this over-parameterized regime, the training loss typically has infinitely many…

Machine Learning · Computer Science 2025-06-23 Kanumuri Nithin Varma , Babak Hassibi

Deep learning algorithms - typically consisting of a class of deep neural networks trained by a stochastic gradient descent (SGD) optimization method - are nowadays the key ingredients in many artificial intelligence (AI) systems and have…

Machine Learning · Computer Science 2024-07-12 Steffen Dereich , Robin Graeber , Arnulf Jentzen

Adaptive gradient methods, especially Adam-type methods (such as Adam, AMSGrad, and AdaBound), have been proposed to speed up the training process with an element-wise scaling term on learning rates. However, they often generalize poorly…

Machine Learning · Computer Science 2021-07-20 Zhou Shao , Tong Lin

A core problem in machine learning is to learn expressive latent variables for model prediction on complex data that involves multiple sub-components in a flexible and interpretable fashion. Here, we develop an approach that improves…

Machine Learning · Computer Science 2024-02-13 Yi-Lin Tuan , Zih-Yun Chiu , William Yang Wang

Motivated by concerns that machine learning algorithms may introduce significant bias in classification models, developing fair classifiers has become an important problem in machine learning research. One important paradigm towards this…

Machine Learning · Computer Science 2019-01-30 L. Elisa Celis , Vijay Keswani

When information acquisition is costly but flexible, a principal may rationally acquire information that favors one group over another. The former group faces incentives to invest in becoming productive, while the latter is discouraged from…

Theoretical Economics · Economics 2024-09-10 Federico Echenique , Anqi Li

The paper presents the formulation, implementation, and evaluation of the ArcGD optimiser. The evaluation is conducted initially on a non-convex benchmark function and subsequently on a real-world ML dataset. The initial comparative study…

Machine Learning · Computer Science 2026-03-25 Nikhil Verma , Joonas Linnosmaa , Leonardo Espinosa-Leal , Napat Vajragupta

We introduce Deep Linear Discriminant Analysis (DeepLDA) which learns linearly separable latent representations in an end-to-end fashion. Classic LDA extracts features which preserve class separability and is used for dimensionality…

Machine Learning · Computer Science 2016-02-18 Matthias Dorfer , Rainer Kelz , Gerhard Widmer

Adaptive optimization algorithms, such as Adam and RMSprop, have shown better optimization performance than stochastic gradient descent (SGD) in some scenarios. However, recent studies show that they often lead to worse generalization…

Machine Learning · Computer Science 2018-09-19 Zijun Zhang , Lin Ma , Zongpeng Li , Chuan Wu

In gradient descent, changing how we parametrize the model can lead to drastically different optimization trajectories, giving rise to a surprising range of meaningful inductive biases: identifying sparse classifiers or reconstructing…

Machine Learning · Statistics 2021-11-24 Anna Kerekes , Anna Mészáros , Ferenc Huszár

Training deep neural networks is a highly nontrivial task, involving carefully selecting appropriate training algorithms, scheduling step sizes and tuning other hyperparameters. Trying different combinations can be quite labor-intensive and…

Machine Learning · Computer Science 2017-06-13 Kaifeng Lv , Shunhua Jiang , Jian Li

Machine learning can provide predictions with disparate outcomes, in which subgroups of the population (e.g., defined by age, gender, or other sensitive attributes) are systematically disadvantaged. In order to comply with upcoming…

Machine Learning · Computer Science 2024-01-25 Moritz von Zahn , Oliver Hinz , Stefan Feuerriegel

Training deep neural networks is a challenging task. In order to speed up training and enhance the performance of deep neural networks, we rectify the vanilla conjugate gradient as conjugate-gradient-like and incorporate it into the generic…

Machine Learning · Computer Science 2025-01-09 Jiawu Tian , Liwei Xu , Xiaowei Zhang , Yongqi Li

Understanding the algorithmic bias of \emph{stochastic gradient descent} (SGD) is one of the key challenges in modern machine learning and deep learning theory. Most of the existing works, however, focus on \emph{very small or even…

Machine Learning · Computer Science 2021-03-30 Jingfeng Wu , Difan Zou , Vladimir Braverman , Quanquan Gu

One of the most popular training algorithms for deep neural networks is the Adaptive Moment Estimation (Adam) introduced by Kingma and Ba. Despite its success in many applications there is no satisfactory convergence analysis: only local…

Machine Learning · Computer Science 2022-10-06 Sebastian Bock , Martin Georg Weiß

One crucial factor behind the success of deep learning lies in the implicit bias induced by noise inherent in gradient-based training algorithms. Motivated by empirical observations that training with noisy labels improves model…

Machine Learning · Computer Science 2026-03-12 Tongcheng Zhang , Zhanpeng Zhou , Mingze Wang , Andi Han , Wei Huang , Taiji Suzuki , Junchi Yan

Although statistical learning theory provides a robust framework to understand supervised learning, many theoretical aspects of deep learning remain unclear, in particular how different architectures may lead to inductive bias when trained…

Machine Learning · Computer Science 2024-03-27 Cédric Gerbelot , Avetik Karagulyan , Stefani Karp , Kavya Ravichandran , Menachem Stern , Nathan Srebro

Here I present a small update to the bias-correction term in the Adam optimizer that has the advantage of making smaller gradient updates in the first several steps of training. With the default bias-correction, Adam may actually make…

Machine Learning · Computer Science 2021-10-25 John St John

The deep learning community has devised a diverse set of methods to make gradient optimization, using large datasets, of large and highly complex models with deeply cascaded nonlinearities, practical. Taken as a whole, these methods…

Machine Learning · Computer Science 2016-11-14 Atılım Güneş Baydin , Barak A. Pearlmutter , Jeffrey Mark Siskind

Linear discriminant analysis (LDA) is a fundamental classification and dimension reduction method that achieves Bayes optimality under Gaussian mixture, but often struggles in high-dimensional settings where the covariance matrix cannot be…

Computation · Statistics 2026-04-06 Cencheng Shen , Yuexiao Dong