English
Related papers

Related papers: SPARLING: Learning Latent Representations with Ext…

200 papers

Sparse Autoencoders uncover thousands of features in vision models, yet explaining these features without requiring human intervention remains an open challenge. While previous work has proposed generating correlation-based explanations…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Javier Ferrando , Enrique Lopez-Cuena , Pablo Agustin Martin-Torres , Daniel Hinjos , Anna Arias-Duart , Dario Garcia-Gasulla

Decomposing model activations into interpretable components is a key open problem in mechanistic interpretability. Sparse autoencoders (SAEs) are a popular method for decomposing the internal activations of trained transformers into sparse,…

Machine Learning · Computer Science 2024-06-26 Connor Kissane , Robert Krzyzanowski , Joseph Isaac Bloom , Arthur Conmy , Neel Nanda

Neural networks are hypothesized to implement interpretable causal mechanisms, yet verifying this requires finding a causal abstraction -- a simpler, high-level Structural Causal Model (SCM) faithful to the network under interventions.…

Machine Learning · Computer Science 2026-03-02 Amir Asiaee

State-space models (SSMs) are a powerful statistical tool for modelling time-varying systems via a latent state. In these models, the latent state is never directly observed. Instead, a sequence of data points related to the state are…

Computation · Statistics 2023-06-22 Benjamin Cox , Victor Elvira

Features based on sparse representation, especially using the synthesis dictionary model, have been heavily exploited in signal processing and computer vision. However, synthesis dictionary learning typically involves NP-hard sparse coding…

Machine Learning · Computer Science 2017-10-17 Bihan Wen , Saiprasad Ravishankar , Yoram Bresler

Imitation learning is an effective alternative approach to learn a policy when the reward function is sparse. In this paper, we consider a challenging setting where an agent and an expert use different actions from each other. We assume…

Machine Learning · Computer Science 2019-08-27 Konrad Zolna , Negar Rostamzadeh , Yoshua Bengio , Sungjin Ahn , Pedro O. Pinheiro

In dictionary learning, also known as sparse coding, the algorithm is given samples of the form $y = Ax$ where $x\in \mathbb{R}^m$ is an unknown random sparse vector and $A$ is an unknown dictionary matrix in $\mathbb{R}^{n\times m}$…

Data Structures and Algorithms · Computer Science 2014-01-06 Sanjeev Arora , Aditya Bhaskara , Rong Ge , Tengyu Ma

We are motivated by problems that arise in a number of applications such as Online Marketing and explosives detection, where the observations are usually modeled using Poisson statistics. We model each observation as a Poisson random…

Statistics Theory · Mathematics 2016-11-17 D. Motamedvaziri , M. H. Rohban , V. Saligrama

In this work, we consider learning sparse models in large scale settings, where the number of samples and the feature dimension can grow as large as millions or billions. Two immediate issues occur under such challenging scenario: (i)…

Machine Learning · Statistics 2023-01-31 Atul Dhingra , Jie Shen , Nicholas Kleene

We investigate an existing distributed algorithm for learning sparse signals or data over networks. The algorithm is iterative and exchanges intermediate estimates of a sparse signal over a network. This learning strategy using exchange of…

Machine Learning · Statistics 2017-09-25 Ahmed Zaki , Partha P. Mitra , Lars K. Rasmussen , Saikat Chatterjee

We consider the estimation of a sparse factor model where the factor loading matrix is assumed sparse. The estimation problem is reformulated as a penalized M-estimation criterion, while the restrictions for identifying the factor loading…

Statistics Theory · Mathematics 2025-01-23 Benjamin Poignard , Yoshikazu Terada

Compressed sensing aims to undersample certain high-dimensional signals, yet accurately reconstruct them by exploiting signal characteristics. Accurate reconstruction is possible when the object to be recovered is sufficiently sparse in a…

Information Theory · Computer Science 2015-05-13 David L. Donoho , Arian Maleki , Andrea Montanari

Sparse autoencoders (SAEs) are a useful tool for uncovering human-interpretable features in the activations of large language models (LLMs). While some expect SAEs to find the true underlying features used by a model, our research shows…

Machine Learning · Computer Science 2025-01-31 Gonçalo Paulo , Nora Belrose

The success of pre-trained contextualized representations has prompted researchers to analyze them for the presence of linguistic information. Indeed, it is natural to assume that these pre-trained representations do encode some level of…

Computation and Language · Computer Science 2025-08-08 Karolina Stańczak , Lucas Torroba Hennigen , Adina Williams , Ryan Cotterell , Isabelle Augenstein

Linear Mixed Models (LMMs) are important tools in statistical genetics. When used for feature selection, they allow to find a sparse set of genetic traits that best predict a continuous phenotype of interest, while simultaneously correcting…

There have been two separate lines of work on estimating Ising models: (1) estimating them from multiple independent samples under minimal assumptions about the model's interaction matrix; and (2) estimating them from one sample in…

Statistics Theory · Mathematics 2020-12-11 Yuval Dagan , Constantinos Daskalakis , Nishanth Dikkala , Anthimos Vardis Kandiros

While Mixture-of-Experts (MoE) scales capacity via conditional computation, Transformers lack a native primitive for knowledge lookup, forcing them to inefficiently simulate retrieval through computation. To address this, we introduce…

Many machine learning applications use latent variable models to explain structure in data, whereby visible variables (= coordinates of the given datapoint) are explained as a probabilistic function of some hidden variables. Finding…

Machine Learning · Computer Science 2016-12-30 Sanjeev Arora , Rong Ge , Tengyu Ma , Andrej Risteski

Imitation learning suffers from causal confusion. This phenomenon occurs when learned policies attend to features that do not causally influence the expert actions but are instead spuriously correlated. Causally confused agents produce low…

Machine Learning · Computer Science 2023-08-14 Samuel Pfrommer , Yatong Bai , Hyunin Lee , Somayeh Sojoudi

We provide explicit, finite-sample guarantees for learning causal representations from data with a sublinear number of environments. Causal representation learning seeks to provide a rigourous foundation for the general representation…

Machine Learning · Statistics 2026-03-30 Inbeom Lee , Tongtong Jin , Bryon Aragam