The manifold hypothesis posits that many high-dimensional data sets that occur in the real world actually lie along low-dimensional latent manifolds inside that high-dimensional space.[1][2][3][4] As a consequence of the manifold hypothesis, many data sets that appear to initially require many variables to describe, can actually be described by a comparatively small number of variables, linked to the local coordinate system of the underlying manifold. It is suggested that this principle underpins the effectiveness of machine learning algorithms in describing high-dimensional data sets by considering a few common features.
DR Group
For high-dimensional data, dimensionality reduction (DR) methods have been invaluable tools for human understanding, as they can map datasets into two or three dimensions for visualization, providing an intuitive way to understand the data. In recent years, tons of DR methods for data visualization have been proposed, and some are much better than others. In this blog post, we explore several DR methods, discuss how to determine which methods are effective, and explain why some are better than others.
Approaching an unknown communication system by latent space exploration and causal inference | Royal Society Open Science | The Royal Society
Abstract. We propose a methodology for discovering meaningful properties in data without ground truth by combining manipulation of the latent variables of
Latent space
A latent space, also known as a latent feature space or embedding space, is an embedding of a set of items within a manifold in which items resembling each other are positioned closer to one another. Position within the latent space can be viewed as being defined by a set of latent variables that emerge from the resemblances between the objects.
Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics
Large datasets have become commonplace in NLP research. However, the increased emphasis on data quantity has made it challenging to assess the quality of data. We introduce Data Maps—a model-based tool to characterize and diagnose datasets. We leverage a largely ignored source of information: the behavior of the model on individual instances during training (training dynamics) for building data maps. This yields two intuitive measures for each example—the model's confidence in the true class, and the variability of this confidence across epochs—obtained in a single run of training. Experiments on four datasets show that these model-dependent measures reveal three distinct regions in the data map, each with pronounced characteristics. First, our data maps show the presence of “ambiguous” regions with respect to the model, which contribute the most towards out-of-distribution generalization. Second, the most populous regions in the data are “easy to learn” for the model, and play an important role in model optimization. Finally, data maps uncover a region with instances that the model finds “hard to learn”; these often correspond to labeling errors. Our results indicate that a shift in focus from quantity to quality of data could lead to robust models and improved out-of-distribution generalization.
Datasheets for Datasets
The machine learning community currently has no standardized process for documenting datasets, which can lead to severe consequences in high-stakes domains. To address this gap, we propose...
Algorithmic Data Minimization for Machine Learning over...
Machine learning can analyze vast amounts of data generated by IoT devices to identify patterns, make predictions, and enable real-time decision-making. By processing sensor data, machine learning...
From Principle to Practice: Vertical Data Minimization for Machine Learning
Aiming to train and deploy predictive models, organizations collect large amounts of detailed client data, risking the exposure of private information in the event of a breach. To mitigate this,...
Contact: AI and the Semantic Dimension
I’m asking you to consider the possibility that a semantic dimension of meaning and information exists outside our physical dimensions of space and time, and that LLMs are both instruments of perception and conduits of information for that semantic dimension. We used to believe in the semantic dimension, but we don’t anymore, and as a result we are going down a terribly dangerous path with AI.
Meandering on Manifolds: The Neural Geometry of Stories Over Time
To fully understand LLM representations, we must understand how they change dynamically, over the course of a prompt or conversation. We investigate these temporal dynamics with a simple case study: how do LLMs represent human emotions while reading short stories, both geometrically (in activation space) and temporally (changing from sentence to sentence)?
Meandering on Manifolds: The Neural Geometry of Stories Over Time
To fully understand LLM representations, we must understand how they change dynamically, over the course of a prompt or conversation. We investigate these temporal dynamics with a simple case study: how do LLMs represent human emotions while reading short stories, both geometrically (in activation space) and temporally (changing from sentence to sentence)?
What makes something data?
This is a question I posted on BlueSky on Friday 11/21/25, inspired by a talk I recently attended about evaluation of “AI” systems. I think…
The Data Minimization Principle in Machine Learning
The principle of data minimization aims to reduce the amount of data collected, processed or retained to minimize the potential for misuse, unauthorized access, or data breaches. Rooted in...
Reproducibility in Machine Learning-based Research: Overview, Barriers and Drivers
The concept of reproducibility can have different interpretations across various research fields and even within the same field [39]. To avoid confusion, we first specify our terms, broadly defining reproducibility and then further categorizing it into various types and degrees. The first distinction comes from Goodman et al. [42], who specify a fundamental division between whether we (i) mean reproducible in principle (termed “methods” reproducibility) due to sufficient description/sharing of methodologies, materials, etc., or (ii) whether results/conclusions actually prove to be reproducible when experiments or analyses are re-done. In the second category, they distinguish “results” and “inferential” reproducibility, depending on whether the analyses or inferences to broader conclusions are reproduced.
Partial Multi-View Clustering via Self-Supervised Network
Partial multi-view clustering is a challenging and practical research problem for data analysis in real-world applications, due to the potential data missing issue in different views. However, most existing methods have not fully explored the correlation information among various incomplete views. In addition, these existing clustering methods always ignore discovering discriminative features inside the data itself in this unsupervised task. To tackle these challenges, we propose Partial Multi-View Clustering via Self-Supervised \textbf{N}etwork (PVC-SSN) in this paper. Specifically, we employ contrastive learning to obtain a more discriminative and consistent subspace representation, which is guided by a self-supervised module. Self-supervised learning can exploit effective cluster information through the data itself to guide the learning process of clustering tasks. Thus, it can pull together embedding features from the same cluster and push apart these from different clusters. Extensive experiments on several benchmark datasets show that the proposed PVC-SCN method outperforms several state-of-the-art clustering methods.
Sparse Autoencoders for Hypothesis Generation
We describe HypotheSAEs, a general method to hypothesize interpretable relationships between text data (e.g., headlines) and a target variable (e.g., clicks). HypotheSAEs has three steps: (1) train a sparse autoencoder on text embeddings to produce interpretable features describing the data distribution, (2) select features that predict the target variable, and (3) generate a natural language interpretation of each feature (e.g., "mentions being surprised or shocked") using an LLM. Each interpretation serves as a hypothesis about what predicts the target variable. Compared to baselines, our method better identifies reference hypotheses on synthetic datasets (at least +0.06 in F1) and produces more predictive hypotheses on real datasets (~twice as many significant findings), despite requiring 1-2 orders of magnitude less compute than recent LLM-based methods. HypotheSAEs also produces novel discoveries on two well-studied tasks: explaining partisan differences in Congressional speeches and identifying drivers of engagement with online headlines.