English
Related papers

Related papers: Margins, Shrinkage, and Boosting

200 papers

We describe PromptBoosting, a query-efficient procedure for building a text classifier from a neural language model (LM) without access to the LM's parameters, gradients, or hidden representations. This form of "black-box" classifier…

Computation and Language · Computer Science 2023-07-04 Bairu Hou , Joe O'Connor , Jacob Andreas , Shiyu Chang , Yang Zhang

The Alternating Direction Method of Multipliers (ADMM) has been studied for years. The traditional ADMM algorithm needs to compute, at each iteration, an (empirical) expected loss function on all training examples, resulting in a…

Machine Learning · Statistics 2014-06-10 Peilin Zhao , Jinwei Yang , Tong Zhang , Ping Li

The choice of batch sizes in minibatch stochastic gradient optimizers is critical in large-scale model training for both optimization and generalization performance. Although large-batch training is arguably the dominant training paradigm…

Machine Learning · Computer Science 2024-05-29 Tim Tsz-Kit Lau , Han Liu , Mladen Kolar

Mini-batch algorithms have been proposed as a way to speed-up stochastic convex optimization problems. We study how such algorithms can be improved using accelerated gradient methods. We provide a novel analysis, which shows how standard…

Machine Learning · Computer Science 2011-06-24 Andrew Cotter , Ohad Shamir , Nathan Srebro , Karthik Sridharan

We study three classical machine learning algorithms in the context of algorithmic fairness: adaptive boosting, support vector machines, and logistic regression. Our goal is to maintain the high accuracy of these learning algorithms while…

Machine Learning · Computer Science 2016-01-22 Benjamin Fish , Jeremy Kun , Ádám D. Lelkes

When using large-batch training to speed up stochastic gradient descent, learning rates must adapt to new batch sizes in order to maximize speed-ups and preserve model quality. Re-tuning learning rates is resource intensive, while fixed…

Machine Learning · Computer Science 2020-07-13 Tyler B. Johnson , Pulkit Agrawal , Haijie Gu , Carlos Guestrin

The recently proposed Muon optimizer updates weight matrices via orthogonalized momentum and has demonstrated strong empirical success in large language model training. However, it remains unclear how to determine the learning rates for…

Machine Learning · Computer Science 2025-09-09 Minxin Zhang , Yuxuan Liu , Hayden Schaeffer

Various bias-correction methods such as EXTRA, gradient tracking methods, and exact diffusion have been proposed recently to solve distributed {\em deterministic} optimization problems. These methods employ constant step-sizes and converge…

Machine Learning · Computer Science 2023-07-19 Kun Yuan , Sulaiman A. Alghunaim , Bicheng Ying , Ali H. Sayed

A framework previously introduced in [3] for solving a sequence of stochastic optimization problems with bounded changes in the minimizers is extended and applied to machine learning problems such as regression and classification. The…

Machine Learning · Computer Science 2019-04-08 Craig Wilson , Yuheng Bu , Venugopal Veeravalli

Based on the use of different exponential bases to define class-dependent error bounds, a new and highly efficient asymmetric boosting scheme, coined as AdaBoostDB (Double-Base), is proposed. Supported by a fully theoretical derivation…

Computer Vision and Pattern Recognition · Computer Science 2015-07-09 Iago Landesa-Vázquez , José Luis Alba-Castro

Gradient clipping is a popular modification to standard (stochastic) gradient descent, at every iteration limiting the gradient norm to a certain value $c >0$. It is widely used for example for stabilizing the training of deep learning…

Machine Learning · Computer Science 2023-11-10 Anastasia Koloskova , Hadrien Hendrikx , Sebastian U. Stich

We design a randomised parallel version of Adaboost based on previous studies on parallel coordinate descent. The algorithm uses the fact that the logarithm of the exponential loss is a function with coordinate-wise Lipschitz continuous…

Machine Learning · Computer Science 2017-04-14 Olivier Fercoq

In this paper we analyze boosting algorithms in linear regression from a new perspective: that of modern first-order methods in convex optimization. We show that classic boosting algorithms in linear regression, namely the incremental…

Statistics Theory · Mathematics 2015-05-19 Robert M. Freund , Paul Grigas , Rahul Mazumder

Gradient tree boosting is a prediction algorithm that sequentially produces a model in the form of linear combinations of decision trees, by solving an infinite-dimensional optimization problem. We combine gradient boosting and Nesterov's…

Machine Learning · Statistics 2018-03-07 Gérard Biau , Benoît Cadre , Laurent Rouvìère

In this work, we propose new adaptive step size strategies that improve several stochastic gradient methods. Our first method (StoPS) is based on the classical Polyak step size (Polyak, 1987) and is an extension of the recent development of…

Machine Learning · Computer Science 2022-08-11 Samuel Horváth , Konstantin Mishchenko , Peter Richtárik

One of the most popular ML algorithms, AdaBoost, can be derived from the dual of a relative entropy minimization problem subject to the fact that the positive weights on the examples sum to one. Essentially, harder examples receive higher…

Machine Learning · Computer Science 2023-06-12 Richard Nock , Ehsan Amid , Manfred K. Warmuth

The popularity of bi-level optimization (BO) in deep learning has spurred a growing interest in studying gradient-based BO algorithms. However, existing algorithms involve two coupled learning rates that can be affected by approximation…

Machine Learning · Computer Science 2023-11-03 Chen Fan , Gaspard Choné-Ducasse , Mark Schmidt , Christos Thrampoulidis

Component-wise gradient boosting algorithms are popular for their intrinsic variable selection and implicit regularization, which can be especially beneficial for very flexible model classes. When estimating generalized additive models for…

Methodology · Statistics 2024-04-15 Alexandra Daub , Andreas Mayr , Boyao Zhang , Elisabeth Bergherr

Stochastic variance reduced methods have shown strong performance in solving finite-sum problems. However, these methods usually require the users to manually tune the step-size, which is time-consuming or even infeasible for some…

Optimization and Control · Mathematics 2023-10-10 Binghui Xie , Chenhan Jin , Kaiwen Zhou , James Cheng , Wei Meng

The principle of boosting in supervised learning involves combining multiple weak classifiers to obtain a stronger classifier. AdaBoost has the reputation to be a perfect example of this approach. This study analyzes the (two classes)…

Machine Learning · Computer Science 2024-02-08 Jean-Marc Brossier , Olivier Lafitte , Lenny Réthoré