English
Related papers

Related papers: Disentangling Linear Mode-Connectivity

200 papers

Deep learning involves navigating a high-dimensional loss landscape over the neural network parameter space. Over the course of training, complex computational structures form and re-form inside the neural network, leading to shifts in…

Machine Learning · Computer Science 2025-08-04 Jesse Hoogland , George Wang , Matthew Farrugia-Roberts , Liam Carroll , Susan Wei , Daniel Murfet

Ultra-reliable and low-latency communications (URLLC) have stringent requirements on quality-of-service and network availability. Due to path loss and shadowing, it is very challenging to guarantee the stringent requirements of URLLC with…

Information Theory · Computer Science 2018-06-19 Changyang She , Zhengchuan Chen , Chenyang Yang , Tony Q. S. Quek , Yonghui Li , Branka Vucetic

Building a theoretical understanding of the capabilities of large language models (LLMs) is vital for our ability to predict and explain the behavior of these systems. Here, we investigate the structure of LLM capabilities by extracting…

Computation and Language · Computer Science 2023-06-21 Ryan Burnell , Han Hao , Andrew R. A. Conway , Jose Hernandez Orallo

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

Modularity is a compelling solution to continual learning (CL), the problem of modeling sequences of related tasks. Learning and then composing modules to solve different tasks provides an abstraction to address the principal challenges of…

Machine Learning · Computer Science 2021-11-16 Oleksiy Ostapenko , Pau Rodriguez , Massimo Caccia , Laurent Charlin

The study of network data in the social and health sciences frequently concentrates on two distinct tasks (1) detecting community structures among nodes and (2) associating covariate information to edge formation. In much of this data, it…

Methodology · Statistics 2021-12-14 Heather Mathews , Alexander Volfovsky

We present a didactic introduction to spectral Dynamic Causal Modelling (DCM), a Bayesian state-space modelling approach used to infer effective connectivity from non-invasive neuroimaging data. Spectral DCM is currently the most widely…

Neurons and Cognition · Quantitative Biology 2023-09-07 Leonardo Novelli , Karl Friston , Adeel Razi

Learning latent structure in complex networks has become an important problem fueled by many types of networked data originating from practically all fields of science. In this paper, we propose a new non-parametric Bayesian…

Social and Information Networks · Computer Science 2015-03-18 Morten Mørup , Mikkel N. Schmidt , Lars Kai Hansen

A common approach to modeling networks assigns each node to a position on a low-dimensional manifold where distance is inversely proportional to connection likelihood. More positive manifold curvature encourages more and tighter…

Methodology · Statistics 2023-01-03 Shane Lubold , Arun G. Chandrasekhar , Tyler H. McCormick

This thesis provides methods and analysis of models which make progress on this goal. The techniques outlined are task agnostic, and should provide benefit when used with nearly any transformer LM. We introduce two new finetuning methods…

Computation and Language · Computer Science 2024-08-30 Davis Yoshida

Recent years have seen growing interest in learning disentangled representations, in which distinct features, such as size or shape, are represented by distinct neurons. Quantifying the extent to which a given representation is disentangled…

Machine Learning · Computer Science 2023-04-06 Louis Mahon , Lei Shah , Thomas Lukasiewicz

When large language models (LLMs) use in-context learning (ICL) to solve a new task, they must infer latent concepts from demonstration examples. This raises the question of whether and how transformers represent latent structures as part…

Machine Learning · Computer Science 2025-09-29 Guan Zhe Hong , Bhavya Vasudeva , Vatsal Sharan , Cyrus Rashtchian , Prabhakar Raghavan , Rina Panigrahy

When circuits are set up and dismantled dynamically in elastic optical networks, spectrum tends to become fragmented in the fiber links. The fragmentation limits the available path choices and may lead to significant blocking of connection…

Networking and Internet Architecture · Computer Science 2022-11-07 Anjali Sharma , Varsha Lohani , Yatindra Nath Singh

Complex systems are large collections of entities that organize themselves into non-trivial structures that can be represented by networks. A key emergent property of such systems is robustness against random failures or targeted attacks…

Physics and Society · Physics 2021-06-14 Arsham Ghavasieh , Massimo Stella , Jacob Biamonte , Manlio De Domenico

Neural collapse ($\mathcal{NC}$) is a phenomenon observed in classification tasks where top-layer representations collapse into their class means, which become equinorm, equiangular and aligned with the classifiers. These behaviours --…

Machine Learning · Computer Science 2024-11-27 Robert Wu , Vardan Papyan

Classifiers that are linear in their parameters, and trained by optimizing a convex loss function, have predictable behavior with respect to changes in the training data, initial conditions, and optimization. Such desirable properties are…

Machine Learning · Computer Science 2020-12-22 Alessandro Achille , Aditya Golatkar , Avinash Ravichandran , Marzia Polito , Stefano Soatto

The goal of language modeling techniques is to capture the statistical and structural properties of natural languages from training corpora. This task typically involves the learning of short range dependencies, which generally model the…

Computation and Language · Computer Science 2017-08-23 Youssef Oualil , Mittul Singh , Clayton Greenberg , Dietrich Klakow

To be included into chatbot systems, Large language models (LLMs) must be aligned with human conversational conventions. However, being trained mainly on web-scraped data gives existing LLMs a voice closer to informational text than actual…

Computation and Language · Computer Science 2024-07-30 Shaz Furniturewala , Kokil Jaidka , Yashvardhan Sharma

Despite their outstanding performance, large language models (LLMs) suffer notorious flaws related to their preference for simple, surface-level textual relations over full semantic complexity of the problem. This proposal investigates a…

Computation and Language · Computer Science 2022-06-20 Michal Štefánik

Robust matrix completion (RMC) is a widely used machine learning tool that simultaneously tackles two critical issues in low-rank data analysis: missing data entries and extreme outliers. This paper proposes a novel scalable and learnable…

Machine Learning · Computer Science 2026-05-22 HanQin Cai , Chandra Kundu , Jialin Liu , Wotao Yin
‹ Prev 1 8 9 10 Next ›