English
Related papers

Related papers: On Learning-Curve Monotonicity for Maximum Likelih…

200 papers

Acquisition of data is a difficult task in many applications of machine learning, and it is only natural that one hopes and expects the population risk to decrease (better performance) monotonically with increasing data points. It turns…

Machine Learning · Computer Science 2022-01-19 Zakaria Mhammedi

Plotting a learner's average performance against the number of training samples results in a learning curve. Studying such curves on one or more data sets is a way to get to a better understanding of the generalization properties of this…

Machine Learning · Computer Science 2020-03-16 Marco Loog , Tom Viering , Alexander Mey

A principal curve serves as a powerful tool for uncovering underlying structures of data through 1-dimensional smooth and continuous representations. On the basis of optimal transport theories, this paper introduces a novel principal curve…

Methodology · Statistics 2025-01-15 Tongseok Lim , Kyeongsik Nam , Jinwon Sohn

Monotone learning describes learning processes in which expected performance consistently improves as the amount of training data increases. However, recent studies challenge this conventional wisdom, revealing significant gaps in the…

Machine Learning · Computer Science 2025-05-22 Ming Li , Chenyi Zhang , Qin Li

Capturing aleatoric uncertainty is a critical part of many machine learning systems. In deep learning, a common approach to this end is to train a neural network to estimate the parameters of a heteroscedastic Gaussian distribution by…

Machine Learning · Computer Science 2022-04-04 Maximilian Seitzer , Arash Tavakoli , Dimitrije Antic , Georg Martius

Distributed learning of probabilistic models from multiple data repositories with minimum communication is increasingly important. We study a simple communication-efficient learning framework that first calculates the local maximum…

Machine Learning · Statistics 2014-10-13 Qiang Liu , Alexander Ihler

Learning monotonic models with respect to a subset of the inputs is a desirable feature to effectively address the fairness, interpretability, and generalization issues in practice. Existing methods for learning monotonic neural networks…

Machine Learning · Computer Science 2022-12-16 Xingchao Liu , Xing Han , Na Zhang , Qiang Liu

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…

Machine Learning · Computer Science 2019-11-26 Tom J. Viering , Alexander Mey , Marco Loog

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. Perhaps surprisingly,…

Machine Learning · Computer Science 2023-11-07 Olivier Bousquet , Amit Daniely , Haim Kaplan , Yishay Mansour , Shay Moran , Uri Stemmer

In this note, we give a short information-theoretic proof of the consistency of the Gaussian maximum likelihood estimator in linear auto-regressive models. Our proof yields nearly optimal non-asymptotic rates for parameter recovery and…

Machine Learning · Computer Science 2024-09-11 Ingvar Ziemann

Learning curves are a fundamental primitive in supervised learning, describing how an algorithm's performance improves with more data and providing a quantitative measure of its generalization ability. Formally, a learning curve plots the…

Machine Learning · Computer Science 2026-04-30 Steve Hanneke , Alkis Kalavasis , Shay Moran , Grigoris Velegkas

The behavior of maximum likelihood estimates (MLEs) and the likelihood ratio statistic in a family of problems involving pointwise nonparametric estimation of a monotone function is studied. This class of problems differs radically from the…

Statistics Theory · Mathematics 2009-09-29 Moulinath Banerjee

Despite the huge progress in myriad generation tasks, pretrained language models (LMs) such as GPT2 still tend to generate repetitive texts with maximization-based decoding algorithms for open-ended generation. We attribute their…

Computation and Language · Computer Science 2023-07-06 Jian Guan , Minlie Huang

Continual learning, the ability of a model to adapt to an ongoing sequence of tasks without forgetting earlier ones, is a central goal of artificial intelligence. To better understand its underlying mechanisms, we study the limitations of…

Machine Learning · Statistics 2026-04-21 Hossein Taheri , Avishek Ghosh , Arya Mazumdar

Can autoregressive large language models (LLMs) learn consistent probability distributions when trained on sequences in different token orders? We prove formally that for any well-defined probability distribution, sequence perplexity is…

Computation and Language · Computer Science 2025-05-14 Xiaoliang Luo , Xinyi Xu , Michael Ramscar , Bradley C. Love

In our previous work we have shown how Bayesian networks can be used for adaptive testing of student skills. Later, we have taken the advantage of monotonicity restrictions in order to learn models fitting data better. This article provides…

Artificial Intelligence · Computer Science 2020-09-16 Martin Plajner , Jiří Vomlel

If you tell a learning model that you prefer an alternative $a$ over another alternative $b$, then you probably expect the model to be monotone, that is, the valuation of $a$ increases, and that of $b$ decreases. Yet, perhaps surprisingly,…

Statistics Theory · Mathematics 2025-10-23 Julien Fageot , Peva Blanchard , Gilles Bareilles , Lê-Nguyên Hoang

Shape restrictions such as monotonicity on functions often arise naturally in statistical modeling. We consider a Bayesian approach to the problem of estimation of a monotone regression function and testing for monotonicity. We construct a…

Statistics Theory · Mathematics 2020-08-05 Moumita Chakraborty , Subhashis Ghosal

We study the average case performance of multi-task Gaussian process (GP) regression as captured in the learning curve, i.e. the average Bayes error for a chosen task versus the total number of examples $n$ for all tasks. For GP covariances…

Machine Learning · Computer Science 2012-11-05 Simon R. F. Ashton , Peter Sollich

Expectation maximization (EM) is the default algorithm for fitting probabilistic models with missing or latent variables, yet we lack a full understanding of its non-asymptotic convergence properties. Previous works show results along the…

Machine Learning · Computer Science 2022-03-01 Frederik Kunstner , Raunak Kumar , Mark Schmidt
‹ Prev 1 2 3 10 Next ›