相关论文: Proper Dataset Valuation by Pointwise Mutual Infor…

Traditional machine learning relies on explicit models and domain assumptions, limiting flexibility and interpretability. We introduce a model-free framework using surprisal (information theoretic uncertainty) to directly analyze and…

Multivariate pattern analyses approaches in neuroimaging are fundamentally concerned with investigating the quantity and type of information processed by various regions of the human brain; typically, estimates of classification accuracy…

To cluster data is to separate samples into distinctive groups that should ideally have some cohesive properties. Today, numerous clustering algorithms exist, and their differences lie essentially in what can be perceived as ``cohesive…

Contrastive learning has emerged as a cornerstone in recent achievements of unsupervised representation learning. Its primary paradigm involves an instance discrimination task with a mutual information loss. The loss is known as InfoNCE and…

In various biomedical studies, analysis often focuses on data magnitudes, particularly when algebraic signs are irrelevant or lost. For repeated measures studies involving magnitude outcomes, incorporating random effects is essential as…

The collection, transfer and integration of research information into different research Information systems can result in different data errors that can have a variety of negative effects on data quality. In order to detect errors at an…

This paper discusses a crowdsourcing based method that we designed to quantify the importance of different attributes of a dataset in determining the outcome of a classification problem. This heuristic, provided by humans acts as the…

Mathematical models of measuring systems and processes play an essential role in metrology and practical measurements. They form the basis for understanding and evaluating measurements, their results and their trustworthiness. Classic…

The goal of information retrieval is to recommend a list of document candidates that are most relevant to a given query. Listwise learning trains neural retrieval models by comparing various candidates simultaneously on a large scale,…

Forecasting techniques for assessing the power of future experiments to discriminate between theories or discover new laws of nature are of great interest in many areas of science. In this paper, we introduce a Bayesian forecasting method…

Dynamic feature selection, where we sequentially query features to make accurate predictions with a minimal budget, is a promising paradigm to reduce feature acquisition costs and provide transparency into a model's predictions. The problem…

Instruction tuning plays a critical role in aligning large language models (LLMs) with human preference. Despite the vast amount of open instruction datasets, naively training a LLM on all existing instructions may not be optimal and…

Information integration plays a pivotal role in biomedical studies by facilitating the combination and analysis of independent datasets from multiple studies, thereby uncovering valuable insights that might otherwise remain obscured due to…

This paper describes a generalizable model evaluation method that can be adapted to evaluate AI/ML models across multiple criteria including core scientific principles and more practical outcomes. Emerging from prediction competitions in…

We formulate meta learning using information theoretic concepts; namely, mutual information and the information bottleneck. The idea is to learn a stochastic representation or encoding of the task description, given by a training set, that…

The problem of model selection is considered for the setting of interpolating estimators, where the number of model parameters exceeds the size of the dataset. Classical information criteria typically consider the large-data limit,…

Dataset distillation (DD) aims to minimize the time and memory consumption needed for training deep neural networks on large datasets, by creating a smaller synthetic dataset that has similar performance to that of the full real dataset.…

Sequential data - ranging from financial time series to natural language - has driven the growing adoption of autoregressive models. However, these algorithms rely on the presence of underlying patterns in the data, and their identification…

We propose a new framework for reasoning about information in complex systems. Our foundation is based on a variational extension of Shannon's information theory that takes into account the modeling power and computational constraints of…

Meta-learning is increasingly used to support the recommendation of machine learning algorithms and their configurations. Such recommendations are made based on meta-data, consisting of performance evaluations of algorithms on prior…