Related papers: HoloClean: Holistic Data Repairs with Probabilisti…

The challenge of creating domain-centric embeddings arises from the abundance of unstructured data and the scarcity of domain-specific structured data. Conventional embedding techniques often rely on either modality, limiting their…

With the rapid development of large language models (LLMs), the quality of training data has become crucial. Among the various types of training data, mathematical data plays a key role in enabling LLMs to acquire strong reasoning…

Machine unlearning seeks to remove the influence of particular data or class from trained models to meet privacy, legal, or ethical requirements. Existing unlearning methods tend to forget shallowly: phenomenon of an unlearned model pretend…

The matrix completion problem aims to reconstruct a low-rank matrix based on a revealed set of possibly noisy entries. Prior works consider completing the entire matrix with generalization error guarantees. However, the completion accuracy…

Most classification models work by first predicting a posterior probability distribution over all classes and then selecting that class with the largest estimated probability. In many settings however, the quality of posterior probability…

Indexing massive data sets is extremely expensive for large scale problems. In many fields, huge amounts of data are currently generated, however extracting meaningful information from voluminous data sets, such as computing similarity…

Large language models (LLMs) have achieved significant performance gains via scaling up model sizes and/or data. However, recent evidence suggests diminishing returns from such approaches, motivating scaling the computation spent at…

The quality of finetuning data is crucial for aligning large language models (LLMs) with human values. Current methods to improve data quality are either labor-intensive or prone to factual errors caused by LLM hallucinations. This paper…

While Large Language Models (LLMs) excel in general domains, their reliability often falls short in scientific problem-solving. The advancement of scientific AI depends on large-scale, high-quality corpora. However, existing scientific…

This paper presents a novel holistic deep learning framework that simultaneously addresses the challenges of vulnerability to input perturbations, overparametrization, and performance instability from different train-validation splits. The…

We present TransClean, a method for detecting false positive predictions of entity matching algorithms under real-world conditions characterized by large-scale, noisy, and unlabeled multi-source datasets that undergo distributional shifts.…

Data cleaning is the initial stage of any machine learning project and is one of the most critical processes in data analysis. It is a critical step in ensuring that the dataset is devoid of incorrect or erroneous data. It can be done…

Data scarcity and noise are important issues in industrial applications of machine learning. However, it is often challenging to devise a scalable and generalized approach to address the fundamental distributional and semantic properties of…

Inherent risk scoring is an important function in anti-money laundering, used for determining the riskiness of an individual during onboarding $\textit{before}$ fraudulent transactions occur. It is, however, often fraught with two…

Insurance companies must manage millions of claims per year. While most of these claims are non-fraudulent, fraud detection is core for insurance companies. The ultimate goal is a predictive model to single out the fraudulent claims and pay…

One way to interject knowledge into clinically impactful forecasting is to use data assimilation, a nonlinear regression that projects data onto a mechanistic physiologic model, instead of a set of functions, such as neural networks. Such…

Data cleaning is a long-standing challenge in data management. While powerful logic and statistical algorithms have been developed to detect and repair data errors in tables, existing algorithms predominantly rely on domain-experts to first…

Contextual information is a valuable cue for Deep Neural Networks (DNNs) to learn better representations and improve accuracy. However, co-occurrence bias in the training dataset may hamper a DNN model's generalizability to unseen scenarios…

We consider an unconstrained continuous optimization problem where, in each iteration, gradient estimates may be arbitrarily corrupted with a probability greater than 1/2. Additionally, function value estimates may exhibit heavy-tailed…

A new type of robust estimation problem is introduced where the goal is to recover a statistical model that has been corrupted after it has been estimated from data. Methods are proposed for "repairing" the model using only the design and…