English
Related papers

Related papers: Margins, Shrinkage, and Boosting

200 papers

We develop new sub-optimality bounds for gradient descent (GD) that depend on the conditioning of the objective along the path of optimization rather than on global, worst-case constants. Key to our proofs is directional smoothness, a…

Machine Learning · Computer Science 2025-01-15 Aaron Mishkin , Ahmed Khaled , Yuanhao Wang , Aaron Defazio , Robert M. Gower

Learning adversarial examples can be formulated as an optimization problem of maximizing the loss function with some box-constraints. However, for solving this induced optimization problem, the state-of-the-art gradient-based methods such…

Machine Learning · Computer Science 2023-02-03 Wei Tao , Lei Bao , Sheng Long , Gaowei Wu , Qing Tao

Two major momentum-based techniques that have achieved tremendous success in optimization are Polyak's heavy ball method and Nesterov's accelerated gradient. A crucial step in all momentum-based methods is the choice of the momentum…

Machine Learning · Statistics 2017-12-21 Vishwak Srinivasan , Adepu Ravi Sankar , Vineeth N Balasubramanian

This paper presents the key algorithmic techniques behind CatBoost, a new gradient boosting toolkit. Their combination leads to CatBoost outperforming other publicly available boosting implementations in terms of quality on a variety of…

Machine Learning · Computer Science 2019-01-23 Liudmila Prokhorenkova , Gleb Gusev , Aleksandr Vorobev , Anna Veronika Dorogush , Andrey Gulin

We present a statistical perspective on boosting. Special emphasis is given to estimating potentially complex parametric or nonparametric models, including generalized linear and additive models as well as regression models for survival…

Methodology · Statistics 2008-12-18 Peter Bühlmann , Torsten Hothorn

Sign Gradient Descent (SignGD) is a simple yet robust optimization method, widely used in machine learning for its resilience to gradient noise and compatibility with low-precision computations. While its empirical performance is well…

Optimization and Control · Mathematics 2025-08-27 Valentin Leplat , Sergio Mayorga , Roland Hildebrand , Alexander Gasnikov

Boosting as gradient descent algorithms is one popular method in machine learning. In this paper a novel Boosting-type algorithm is proposed based on restricted gradient descent with structural sparsity control whose underlying dynamics are…

Machine Learning · Statistics 2017-04-18 Chendi Huang , Xinwei Sun , Jiechao Xiong , Yuan Yao

In this work, we propose a new optimization framework for multiclass boosting learning. In the literature, AdaBoost.MO and AdaBoost.ECC are the two successful multiclass boosting algorithms, which can use binary weak learners. We explicitly…

Machine Learning · Computer Science 2010-09-21 Zhihui Hao , Chunhua Shen , Nick Barnes , Bo Wang

The "fast iterative shrinkage-thresholding algorithm", a.k.a. FISTA, is one of the most well-known first-order optimisation scheme in the literature, as it achieves the worst-case $O(1/k^2)$ optimal convergence rate in terms of objective…

Optimization and Control · Mathematics 2021-01-21 Jingwei Liang , Tao Luo , Carola-Bibiane Schönlieb

The local gradient points to the direction of the steepest slope in an infinitesimal neighborhood. An optimizer guided by the local gradient is often trapped in local optima when the loss landscape is multi-modal. A directional Gaussian…

Machine Learning · Computer Science 2020-11-05 Hoang Tran , Guannan Zhang

In this work, to efficiently help escape the stationary and saddle points, we propose, analyze, and generalize a stochastic strategy performed as an operator for a first-order gradient descent algorithm in order to increase the target…

Machine Learning · Computer Science 2022-05-23 Wei Zhang , Yu Bao

Despite their overwhelming capacity to overfit, deep neural networks trained by specific optimization algorithms tend to generalize well to unseen data. Recently, researchers explained it by investigating the implicit regularization effect…

Machine Learning · Computer Science 2021-12-17 Bohan Wang , Qi Meng , Wei Chen , Tie-Yan Liu

We study a new aggregation operator for gradients coming from a mini-batch for stochastic gradient (SG) methods that allows a significant speed-up in the case of sparse optimization problems. We call this method AdaBatch and it only…

Machine Learning · Computer Science 2017-11-07 Alexandre Défossez , Francis Bach

We investigate the stochastic gradient descent (SGD) method where the step size lies within a banded region instead of being given by a fixed formula. The optimal convergence rate under mild conditions and large initial step size is proved.…

Optimization and Control · Mathematics 2023-04-10 Xiaoyu Wang , Ya-xiang Yuan

The ``fast iterative shrinkage-thresholding algorithm'', a.k.a. FISTA, is one of the most widely used algorithms in the literature. However, despite its optimal theoretical $O(1/k^2)$ convergence rate guarantee, oftentimes in practice its…

Optimization and Control · Mathematics 2018-07-12 Jingwei Liang , Carola-Bibiane Schönlieb

We introduce MADGRAD, a novel optimization method in the family of AdaGrad adaptive gradient methods. MADGRAD shows excellent performance on deep learning optimization problems from multiple fields, including classification and…

Machine Learning · Computer Science 2021-08-27 Aaron Defazio , Samy Jelassi

We introduce Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments. The method is straightforward to implement, is computationally efficient, has…

Machine Learning · Computer Science 2017-01-31 Diederik P. Kingma , Jimmy Ba

We study gradient descent (GD) with a constant stepsize for $\ell_2$-regularized logistic regression with linearly separable data. Classical theory suggests small stepsizes to ensure monotonic reduction of the optimization objective,…

Machine Learning · Statistics 2025-11-04 Jingfeng Wu , Pierre Marion , Peter Bartlett

Data augmentation (DA) is commonly used during model training, as it significantly improves test error and model robustness. DA artificially expands the training set by applying random noise, rotations, crops, or even adversarial…

Machine Learning · Computer Science 2019-05-09 Shashank Rajput , Zhili Feng , Zachary Charles , Po-Ling Loh , Dimitris Papailiopoulos

We give a general recipe for derandomising PAC-Bayesian bounds using margins, with the critical ingredient being that our randomised predictions concentrate around some value. The tools we develop straightforwardly lead to margin bounds for…

Machine Learning · Computer Science 2022-02-24 Felix Biggs , Benjamin Guedj