English
Related papers

Related papers: What killed the Convex Booster ?

200 papers

Boosting algorithms produce a classifier by iteratively combining base hypotheses. It has been observed experimentally that the generalization error keeps improving even after achieving zero training error. One popular explanation…

Machine Learning · Computer Science 2019-01-31 Allan Grønlund , Kasper Green Larsen , Alexander Mathiasen

The notion of implicit bias, or implicit regularization, has been suggested as a means to explain the surprising generalization ability of modern-days overparameterized learning algorithms. This notion refers to the tendency of the…

Machine Learning · Computer Science 2020-12-23 Assaf Dauber , Meir Feder , Tomer Koren , Roi Livni

It is fair to say that many of the prominent examples of bias in Machine Learning (ML) arise from bias that is there in the training data. In fact, some would argue that supervised ML algorithms cannot be biased, they reflect the data on…

Machine Learning · Computer Science 2021-04-30 William Blanzeisky , Pádraig Cunningham

Recently, self-supervised learning has attracted great attention, since it only requires unlabeled data for model training. Contrastive learning is one popular method for self-supervised learning and has achieved promising empirical…

Machine Learning · Computer Science 2023-03-03 Weiran Huang , Mingyang Yi , Xuyang Zhao , Zihao Jiang

It has recently been shown that supervised learning with the popular logistic loss is equivalent to optimizing the exponential loss over sufficient statistics about the class: Rademacher observations (rados). We first show that this…

Machine Learning · Computer Science 2016-02-16 Richard Nock

We study losses for binary classification and class probability estimation and extend the understanding of them from margin losses to general composite losses which are the composition of a proper loss with a link function. We characterise…

Machine Learning · Statistics 2009-12-18 Mark D. Reid , Robert C. Williamson

We study consistency properties of surrogate loss functions for general multiclass learning problems, defined by a general multiclass loss matrix. We extend the notion of classification calibration, which has been studied for binary and…

Machine Learning · Computer Science 2015-08-25 Harish G. Ramaswamy , Shivani Agarwal

At the heart of machine learning lies the question of generalizability of learned rules over previously unseen data. While over-parameterized models based on neural networks are now ubiquitous in machine learning applications, our…

Machine Learning · Computer Science 2020-05-04 Melikasadat Emami , Mojtaba Sahraee-Ardakan , Parthe Pandit , Sundeep Rangan , Alyson K. Fletcher

The theory of bias-variance used to serve as a guide for model selection when applying Machine Learning algorithms. However, modern practice has shown success with over-parameterized models that were expected to overfit but did not. This…

Machine Learning · Computer Science 2022-11-21 Luis Sa-Couto , Jose Miguel Ramos , Miguel Almeida , Andreas Wichert

Understanding the fundamental mechanism behind the success of transformer networks is still an open problem in the deep learning literature. Although their remarkable performance has been mostly attributed to the self-attention mechanism,…

Machine Learning · Computer Science 2022-11-23 Tolga Ergen , Behnam Neyshabur , Harsh Mehta

We conjecture that the inherent difference in generalisation between adaptive and non-adaptive gradient methods in deep learning stems from the increased estimation noise in the flattest directions of the true loss surface. We demonstrate…

Machine Learning · Statistics 2022-03-17 Diego Granziol , Nicholas Baskerville

Self-supervised learning (especially contrastive learning) has attracted great interest due to its huge potential in learning discriminative representations in an unsupervised manner. Despite the acknowledged successes, existing contrastive…

Computer Vision and Pattern Recognition · Computer Science 2021-10-22 Guangrun Wang , Keze Wang , Guangcong Wang , Philip H. S. Torr , Liang Lin

The pursuit of computational efficiency has driven the adoption of low-precision formats for training transformer models. However, this progress is often hindered by notorious training instabilities. This paper provides the first…

Machine Learning · Computer Science 2026-04-21 Haiquan Qiu , Quanming Yao

Boosting is a widely used machine learning approach based on the idea of aggregating weak learning rules. While in statistical learning numerous boosting methods exist both in the realizable and agnostic settings, in online learning they…

Machine Learning · Computer Science 2020-03-04 Nataly Brukhim , Xinyi Chen , Elad Hazan , Shay Moran

In this tutorial paper, we first define mean squared error, variance, covariance, and bias of both random variables and classification/predictor models. Then, we formulate the true and generalization errors of the model for both training…

Machine Learning · Statistics 2023-05-23 Benyamin Ghojogh , Mark Crowley

There has been a recent surge of interest in the study of asymptotic reconstruction performance in various cases of generalized linear estimation problems in the teacher-student setting, especially for the case of i.i.d standard normal…

Machine Learning · Statistics 2023-02-20 Cedric Gerbelot , Alia Abbara , Florent Krzakala

We study the problem of learning vector-valued linear predictors: these are prediction rules parameterized by a matrix that maps an $m$-dimensional feature vector to a $k$-dimensional target. We focus on the fundamental case with a convex…

Machine Learning · Computer Science 2024-12-06 Matan Schliserman , Tomer Koren

Matrix sensing problems exhibit pervasive non-convexity, plaguing optimization with a proliferation of suboptimal spurious solutions. Avoiding convergence to these critical points poses a major challenge. This work provides new theoretical…

Optimization and Control · Mathematics 2024-03-12 Ziye Ma , Ying Chen , Javad Lavaei , Somayeh Sojoudi

Metric learning seeks perceptual embeddings where visually similar instances are close and dissimilar instances are apart, but learned representations can be sub-optimal when the distribution of intra-class samples is diverse and distinct…

Machine Learning · Computer Science 2021-08-30 Elad Levi , Tete Xiao , Xiaolong Wang , Trevor Darrell

We study a robust online convex optimization framework, where an adversary can introduce outliers by corrupting loss functions in an arbitrary number of rounds k, unknown to the learner. Our focus is on a novel setting allowing unbounded…

Machine Learning · Computer Science 2024-08-13 Adarsh Barik , Anand Krishna , Vincent Y. F. Tan