English
Related papers

Related papers: On Model Stability as a Function of Random Seed

200 papers

In the early 1980s Halbert White inaugurated a "model-robust'' form of statistical inference based on the "sandwich estimator'' of standard error. This estimator is known to be "heteroskedasticity-consistent", but it is less well-known to…

Randomized Controlled Trials (RCTs) may suffer from limited scope. In particular, samples may be unrepresentative: some RCTs over- or under- sample individuals with certain characteristics compared to the target population, for which one…

Methodology · Statistics 2024-03-15 Bénédicte Colnet , Julie Josse , Gaël Varoquaux , Erwan Scornet

The same machine learning model running on different edge devices may produce highly-divergent outputs on a nearly-identical input. Possible reasons for the divergence include differences in the device sensors, the device's signal…

Machine Learning · Computer Science 2020-10-20 Eyal Cidon , Evgenya Pergament , Zain Asgar , Asaf Cidon , Sachin Katti

The class of $\alpha$-stable distributions is widely used in various applications, especially for modelling heavy-tailed data. Although the $\alpha$-stable distributions have been used in practice for many years, new methods for…

Methodology · Statistics 2022-12-29 Kewin Pączek , Damian Jelito , Marcin Pitera , Agnieszka Wyłomańska

For many machine learning algorithms, two main assumptions are required to guarantee performance. One is that the test data are drawn from the same distribution as the training data, and the other is that the model is correctly specified.…

Machine Learning · Computer Science 2020-02-03 Kun Kuang , Ruoxuan Xiong , Peng Cui , Susan Athey , Bo Li

Randomly perturbing networks during the training process is a commonly used approach to improving generalization performance. In this paper, we present a theoretical study of one particular way of random perturbation, which corresponds to…

Machine Learning · Computer Science 2021-02-16 Oussama Dhifallah , Yue M. Lu

The nested error regression model is a useful tool for analyzing clustered (grouped) data, and is especially used in small area estimation. The classical nested error regression model assumes normality of random effects and error terms, and…

Methodology · Statistics 2016-05-16 Shonosuke Sugasawa , Tatsuya Kubokawa

A new approach called NAF (the Neural Attention Forest) for solving regression and classification tasks under tabular training data is proposed. The main idea behind the proposed NAF model is to introduce the attention mechanism into the…

Machine Learning · Computer Science 2023-04-13 Andrei V. Konstantinov , Lev V. Utkin , Alexey A. Lukashin , Vladimir A. Muliukha

We study a genetic regulatory network model developed to demonstrate that genetic robustness can evolve through stabilizing selection for optimal phenotypes. We report preliminary results on whether such selection could result in a…

Molecular Networks · Quantitative Biology 2010-12-07 Volkan Sevim , Per Arne Rikvold

Enhancing the stability of machine learning algorithms under distributional shifts is at the heart of the Out-of-Distribution (OOD) Generalization problem. Derived from causal learning, recent works of invariant learning pursue strict…

Machine Learning · Computer Science 2024-02-15 Jiashuo Liu , Jiayun Wu , Jie Peng , Xiaoyu Wu , Yang Zheng , Bo Li , Peng Cui

We present a causal view on the robustness of neural networks against input manipulations, which applies not only to traditional classification tasks but also to general measurement data. Based on this view, we design a deep causal…

Machine Learning · Computer Science 2021-02-11 Cheng Zhang , Kun Zhang , Yingzhen Li

In adversarial machine learning, deep neural networks can fit the adversarial examples on the training dataset but have poor generalization ability on the test set. This phenomenon is called robust overfitting, and it can be observed when…

Machine Learning · Computer Science 2022-11-01 Jiancong Xiao , Yanbo Fan , Ruoyu Sun , Jue Wang , Zhi-Quan Luo

We tackle here a specific, still not widely addressed aspect, of AI robustness, which consists of seeking invariance / insensitivity of model performance to hidden factors of variations in the data. Towards this end, we employ a two step…

Machine Learning · Computer Science 2022-03-04 William Paul , Philippe Burlina

Model alignment is currently applied in a vacuum, evaluated primarily through standardised benchmark performance. The purpose of this study is to examine the effects of alignment on populations of models through time. We focus on the…

Artificial Intelligence · Computer Science 2026-04-08 Jonathan Elsworth Eicher

Causal inference requires evaluating models on balanced distributions between treatment and control groups, while training data often exhibits imbalance due to historical decision-making policies. Most conventional statistical methods…

Machine Learning · Statistics 2025-11-21 Akira Tanimoto

Training stability is typically regarded as a prerequisite for reliable optimization in large language models. In this work, we analyze how stabilizing training dynamics affects the induced generation distribution. We show that under…

Artificial Intelligence · Computer Science 2026-02-10 Xianzhe Meng , Qiangsheng Zeng , Ling Luo , Qinghan Yang , Jiarui Hao , Wenbo Wu , Qinyu Wang , Rui Yin , Lin Qi , Renzhi Lu

Estimating causal effects from observational data is a central problem in many domains. A general approach is to balance covariates with weights such that the distribution of the data mimics randomization. We present generalized balancing…

Machine Learning · Statistics 2023-10-02 Yoshiaki Kitazawa

Self-paced learning and hard example mining re-weight training instances to improve learning accuracy. This paper presents two improved alternatives based on lightweight estimates of sample uncertainty in stochastic gradient descent (SGD):…

Machine Learning · Statistics 2018-01-09 Haw-Shiuan Chang , Erik Learned-Miller , Andrew McCallum

We introduce a new approach for prudent risk evaluation based on stochastic dominance, which will be called the model aggregation (MA) approach. In contrast to the classic worst-case risk (WR) approach, the MA approach produces not only a…

Risk Management · Quantitative Finance 2024-06-11 Tiantian Mao , Ruodu Wang , Qinyu Wu

When training a machine learning model with observational data, it is often encountered that some values are systemically missing. Learning from the incomplete data in which the missingness depends on some covariates may lead to biased…

Machine Learning · Computer Science 2018-12-24 Kanghoon Lee , Jihye Choi , Moonsu Cha , Jung-Kwon Lee , Taeyoon Kim
‹ Prev 1 4 5 6 7 8 10 Next ›