paper-with-me

Papers

Smoothly Giving up: Robustness for Simple Models

2023-02-17 · Tyler Sypherd, Nathan Stromberg, Richard Nock, Visar Berisha, Lalitha Sankar

There is a growing need for models that are interpretable and have reduced energy and computational cost (e.g., in health care analytics and federated learning). Examples of algorithms to train such models include logistic regression and boosting. However, one challenge facing these algorithms is that they provably suffer from label noise; this has been attributed to the joint interaction between oft-used convex loss functions and simpler hypothesis classes, resulting in too much emphasis being placed on outliers. In this work, we use the margin-based $\alpha$-loss, which continuously tunes between canonical convex and quasi-convex losses, to robustly train simple models. We show that the $\alpha$ hyperparameter smoothly introduces non-convexity and offers the benefit of "giving up" on noisy training examples. We also provide results on the Long-Servedio dataset for boosting and a COVID-19 survey dataset for logistic regression, highlighting the efficacy of our approach across multiple relevant domains.

📄 PDF Abstract BibTeX arXiv:2302.09114

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learningregression

Methods 이 논문이 사용한 방법론

Logistic Regression Logistic Regression, despite its name, is a linear model for classification rather than regression. Logistic regression is also known in the literature as logit regression,…

Similar Papers 제목 키워드 기반

GP-VAE: Deep Probabilistic Time Series Imputation

2019-07-09 · Vincent Fortuin, Dmitry Baranchuk, Gunnar Rätsch, Stephan Mandt

Multivariate time series with missing values are common in areas such as healthcare and finance, and have grown in number and complexity over the years. This raises the question whether deep learning methodologies can ou…

Deep LearningDimensionality ReductionImputationMissing Values+3

Deep Amortized Variational Inference for Multivariate Time Series Imputation with Latent Gaussian Process Models

2019-10-16 · pproximateinference AABI Symposium 2019 12 · Vincent Fortuin, Dmitry Baranchuk, Gunnar Rätsch, Stephan Mandt

Multivariate time series with missing values are common in areas such as healthcare and finance, and have grown in number and complexity over the years. This raises the question whether deep learning methodologies can ou…

Deep LearningDimensionality ReductionImputationMissing Values+4

On the Robustness of Neural Collapse and the Neural Collapse of Robustness

2023-11-13 · Jingtong Su, Ya Shi Zhang, Nikolaos Tsilivis, Julia Kempe

Neural Collapse refers to the curious phenomenon in the end of training of a neural network, where feature vectors and classification weights converge to a very simple geometrical arrangement (a simplex). While it has be…

Diffusion Operator Geometry of Feedforward Representations

2026-05-01 · Kanishka Reddy arxiv

Feedforward neural networks transform data through learned representations whose geometry shapes how classes separate and relate across successive layers. We study that geometry through diffusion operators. Each feature-…

Simple2Complex: Global Optimization by Gradient Descent

2016-05-02 · Ming Li

A method named simple2complex for modeling and training deep neural networks is proposed. Simple2complex train deep neural networks by smoothly adding more and more layers to the shallow networks, as the learning procedu…

global-optimization