English
Related papers

Related papers: Dropout as a Regularizer of Interaction Effects

200 papers

Unsupervised pretraining and dropout have been well studied, especially with respect to regularization and output consistency. However, our understanding about the explicit convergence rates of the parameter estimates, and their dependence…

Machine Learning · Computer Science 2017-02-23 Vamsi K. Ithapu , Sathya Ravi , Vikas Singh

The "power of choice" has been shown to radically alter the behavior of a number of randomized algorithms. Here we explore the effects of choice on models of tree and network growth. In our models each new node has k randomly chosen…

Statistical Mechanics · Physics 2009-11-13 Raissa M. D'Souza , Paul L. Krapivsky , Cristopher Moore

The study of spreading processes often analyzes networks at different resolutions, e.g., at the level of individuals or countries, but it is not always clear how properties at one resolution can carry over to another. Accordingly, in this…

Physics and Society · Physics 2024-12-04 Baike She , Matthew Hale

Regularization plays a major role in modern deep learning. From classic techniques such as L1,L2 penalties to other noise-based methods such as Dropout, regularization often yields better generalization properties by avoiding overfitting.…

Machine Learning · Statistics 2021-06-08 Soufiane Hayou , Fadhel Ayed

Subword regularization, used widely in NLP, improves model performance by reducing the dependency on exact tokenizations, augmenting the training corpus, and exposing the model to more unique contexts during training. BPE and MaxMatch, two…

Computation and Language · Computer Science 2024-08-22 Marco Cognetta , Vilém Zouhar , Naoaki Okazaki

Direct Preference Optimization (DPO) and its variants have become increasingly popular for aligning language models with human preferences. These methods aim to teach models to better distinguish between chosen (or preferred) and rejected…

Computation and Language · Computer Science 2025-06-09 Xiliang Yang , Feng Jiang , Qianen Zhang , Lei Zhao , Xiao Li

In longitudinal studies, subjects may be lost to follow-up, or miss some of the planned visits, leading to incomplete response sequences. When the probability of non-response, conditional on the available covariates and the observed…

Methodology · Statistics 2017-07-10 Alessandra Spagnoli , Maria Francesca Marino , Marco Alfò

This paper analyzes the dynamics of higher education dropouts through an innovative approach that integrates recurrent events modeling and point process theory with functional data analysis. We propose a novel methodology that extends…

Applications · Statistics 2026-03-02 Alessandra Ragni , Chiara Masci , Anna Maria Paganoni

Existing AI alignment approaches assume that preferences are static, which is unrealistic: our preferences change, and may even be influenced by our interactions with AI systems themselves. To clarify the consequences of incorrectly…

Artificial Intelligence · Computer Science 2024-05-29 Micah Carroll , Davis Foote , Anand Siththaranjan , Stuart Russell , Anca Dragan

Statistics of drawdowns (loss from the last local maximum to the next local minimum) plays an important role in risk assessment of investment strategies. As they incorporate higher ($>$ two) order correlations, they offer a better measure…

Condensed Matter · Physics 2009-11-07 Anders Johansen

We investigate the convergence and convergence rate of stochastic training algorithms for Neural Networks (NNs) that have been inspired by Dropout (Hinton et al., 2012). With the goal of avoiding overfitting during training of NNs, dropout…

Optimization and Control · Mathematics 2023-03-24 Albert Senen-Cerda , Jaron Sanders

We consider the problem of learning about and comparing the consequences of dynamic treatment strategies on the basis of observational data. We formulate this within a probabilistic decision-theoretic framework. Our approach is compared…

Statistics Theory · Mathematics 2010-11-16 A. Philip Dawid , Vanessa Didelez

This paper addresses the design of a state observer for networked systems with random delays and dropouts. The model of plant and network covers the cases of multiple sensors, out-of-sequence and buffered measurements. The measurement…

Optimization and Control · Mathematics 2014-03-21 Daniel Dolz , Daniel E. Quevedo , Ignacio Peñarrocha , Roberto Sanchis

Gene regulatory network inference (GRNI) is a challenging problem, particularly owing to the presence of zeros in single-cell RNA sequencing data: some are biological zeros representing no gene expression, while some others are technical…

Quantitative Methods · Quantitative Biology 2024-03-26 Haoyue Dai , Ignavier Ng , Gongxu Luo , Peter Spirtes , Petar Stojanov , Kun Zhang

We address the problem of efficiently and informatively quantifying how multiplets of variables carry information about the future of the dynamical system they belong to. In particular we want to identify groups of variables carrying…

Neurons and Cognition · Quantitative Biology 2020-08-03 Sebastiano Stramaglia , Tomas Scagliarini , Bryan C. Daniels , Daniele Marinazzo

This paper addresses the problem of designing recommendation systems for social networks and e-commerce platforms from a control-theoretic perspective. We treat the design of recommendation systems as a state-feedback infinite-horizon…

Systems and Control · Electrical Eng. & Systems 2026-03-12 Simone Mariano , Paolo Frasca

Dynamical systems across many disciplines are modeled as interacting particles or agents, with interaction rules that depend on a very small number of variables (e.g. pairwise distances, pairwise differences of phases, etc...), functions of…

Machine Learning · Computer Science 2022-08-05 Jinchao Feng , Mauro Maggioni , Patrick Martin , Ming Zhong

We study population dynamics under which each revising agent tests each strategy k times, with each trial being against a newly drawn opponent, and chooses the strategy whose mean payoff was highest. When k = 1, defection is globally stable…

Theoretical Economics · Economics 2021-01-05 Srinivas Arigapudi , Yuval Heller , Igal Milchtaich

A major challenge in training deep neural networks is overfitting, i.e. inferior performance on unseen test examples compared to performance on training examples. To reduce overfitting, stochastic regularization methods have shown superior…

Neural and Evolutionary Computing · Computer Science 2018-04-24 Najeeb Khan , Jawad Shah , Ian Stavness

Deep time series models are vulnerable to noisy data ubiquitous in real-world applications. Existing robustness strategies either prune data or rely on costly prior quantification, failing to balance effectiveness and efficiency. In this…

Artificial Intelligence · Computer Science 2026-05-26 Siru Zhong , Yiqiu Liu , Zhiqing Cui , Zezhi Shao , Fei Wang , Qingsong Wen , Yuxuan Liang