paper-with-me

홈 › Papers

Making Learners (More) Monotone

2019-11-25 · Tom J. Viering, Alexander Mey, Marco Loog

Learning performance can show non-monotonic behavior. That is, more data does not necessarily lead to better models, even on average. We propose three algorithms that take a supervised learning model and make it perform more monotone. We prove consistency and monotonicity with high probability, and evaluate the algorithms on scenarios where non-monotone behaviour occurs. Our proposed algorithm $\text{MT}_{\text{HT}}$ makes less than $1\%$ non-monotone decisions on MNIST while staying competitive in terms of error rate compared to several baselines.

📄 PDF Abstract BibTeX arXiv:1911.11030

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Mapping Monotonic Restrictions in Inductive Inference

2020-10-15 · Vanja Doskoč, Timo Kötzing

In language learning in the limit we investigate computable devices (learners) learning formal languages. Through the years, many natural restrictions have been imposed on the studied learners. As such, monotonic restric…

Robustly Learning Monotone Generalized Linear Models via Data Augmentation

2025-02-12 · Nikos Zarifis, Puqian Wang, Ilias Diakonikolas, Jelena Diakonikolas

We study the task of learning Generalized Linear models (GLMs) in the agnostic model under the Gaussian distribution. We give the first polynomial-time algorithm that achieves a constant-factor approximation for \textit{…

Data Augmentation

Monotone Learning

2022-02-10 · Olivier Bousquet, Amit Daniely, Haim Kaplan, Yishay Mansour 외

The amount of training-data is one of the key factors which determines the generalization capacity of learning algorithms. Intuitively, one expects the error rate to decrease as the amount of training-data increases. Per…

Binary ClassificationClassificationPAC learning

Online Monotone Optimization

2016-08-29 · Ian Gemp, Sridhar Mahadevan

This paper presents a new framework for analyzing and designing no-regret algorithms for dynamic (possibly adversarial) systems. The proposed framework generalizes the popular online convex optimization framework and ext…

LCDB 1.1: A Database Illustrating Learning Curves Are More Ill-Behaved Than Previously Thought

2025-05-21 · Cheng Yan, Felix Mohr, Tom Viering

Sample-wise learning curves plot performance versus training set size. They are useful for studying scaling laws and speeding up hyperparameter tuning and model selection. Learning curves are often assumed to be well-beh…

Model Selection