English
Related papers

Related papers: Mechanistic Mode Connectivity

200 papers

Despite the significant potential of Foundation Models (FMs) in medical imaging, their application to prognosis prediction remains challenging due to data scarcity, class imbalance, and task complexity, which limit their clinical adoption.…

Computer Vision and Pattern Recognition · Computer Science 2026-01-16 Filippo Ruffini , Elena Mulero Ayllon , Linlin Shen , Paolo Soda , Valerio Guarrasi

In this paper, we study a simple and generic framework to tackle the problem of learning model parameters when a fraction of the training samples are corrupted. We first make a simple observation: in a variety of such settings, the…

Machine Learning · Computer Science 2019-02-20 Yanyao Shen , Sujay Sanghavi

Recent studies have shown that many deep metric learning loss functions perform very similarly under the same experimental conditions. One potential reason for this unexpected result is that all losses let the network focus on similar image…

Computer Vision and Pattern Recognition · Computer Science 2022-05-06 Konstantin Kobs , Michael Steininger , Andrzej Dulny , Andreas Hotho

Currently, deep neural networks are deployed on low-power portable devices by first training a full-precision model using powerful hardware, and then deriving a corresponding low-precision model for efficient inference on such systems.…

Machine Learning · Computer Science 2017-11-15 Hao Li , Soham De , Zheng Xu , Christoph Studer , Hanan Samet , Tom Goldstein

A visual system has to learn both which features to extract from images and how to group locations into (proto-)objects. Those two aspects are usually dealt with separately, although predictability is discussed as a cue for both. To…

Computer Vision and Pattern Recognition · Computer Science 2022-05-31 Heiko H. Schütt , Wei Ji Ma

Convolutional neural networks require numerous data for training. Considering the difficulties in data collection and labeling in some specific tasks, existing approaches generally use models pre-trained on a large source domain (e.g.…

Computer Vision and Pattern Recognition · Computer Science 2019-09-06 Zhichen Zhao , Bowen Zhang , Yuning Jiang , Li Xu , Lei Li , Wei-Ying Ma

Randomly connected neural networks have long served as a theoretical tool for studying collective dynamics in neural populations, yet quantitative comparisons to experiments remain limited. Recent technological advances have made it…

Neurons and Cognition · Quantitative Biology 2026-05-27 Zehui Zhao , Michael J Pasek , Ilya M Nemenman

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

Fine-tuning is arguably the most straightforward way to tailor a pre-trained model (e.g., a foundation model) to downstream applications, but it also comes with the risk of losing valuable knowledge the model had learned in pre-training.…

Modeling the behavior of coupled networks is challenging due to their intricate dynamics. For example in neuroscience, it is of critical importance to understand the relationship between the functional neural processes and anatomical…

Machine Learning · Computer Science 2021-04-20 Hongyuan You , Sikun Lin , Ambuj K. Singh

An approach to improve neural network interpretability is via clusterability, i.e., splitting a model into disjoint clusters that can be studied independently. We define a measure for clusterability and show that pre-trained models form…

Machine Learning · Computer Science 2025-07-28 Satvik Golechha , Maheep Chaudhary , Joan Velja , Alessandro Abate , Nandi Schoots

With the emergence of large-scale pre-trained neural networks, methods to adapt such "foundation" models to data-limited downstream tasks have become a necessity. Fine-tuning, preference optimization, and transfer learning have all been…

Machine Learning · Statistics 2025-07-09 Javan Tahir , Surya Ganguli , Grant M. Rotskoff

To enhance the reproducibility and reliability of deep learning models, we address a critical gap in current training methodologies: the lack of mechanisms that ensure consistent and robust performance across runs. Our empirical analysis…

Machine Learning · Computer Science 2026-01-05 Waqas Ahmed , Sheeba Samuel , Kevin Coakley , Birgitta Koenig-Ries , Odd Erik Gundersen

We study the ability of foundation models to learn representations for classification that are transferable to new, unseen classes. Recent results in the literature show that representations learned by a single classifier over many classes…

Machine Learning · Computer Science 2023-07-18 Tomer Galanti , András György , Marcus Hutter

Recently, Ainsworth et al. showed that using weight matching (WM) to minimize the $L^2$ distance in a permutation search of model parameters effectively identifies permutations that satisfy linear mode connectivity (LMC), where the loss…

Machine Learning · Computer Science 2025-04-09 Akira Ito , Masanori Yamada , Atsutoshi Kumagai

A machine learning (ML) feature network is a graph that connects ML features in learning tasks based on their similarity. This network representation allows us to view feature vectors as functions on the network. By leveraging function…

Machine Learning · Statistics 2024-01-11 Xinying Mu , Mark Kon

While the research on convolutional neural networks (CNNs) is progressing quickly, the real-world deployment of these models is often limited by computing resources and memory constraints. In this paper, we address this issue by proposing a…

Computer Vision and Pattern Recognition · Computer Science 2018-03-16 Dong Wang , Lei Zhou , Xueni Zhang , Xiao Bai , Jun Zhou

Sharpness of minima is a promising quantity that can correlate with generalization in deep networks and, when optimized during training, can improve generalization. However, standard sharpness is not invariant under reparametrizations of…

Machine Learning · Computer Science 2023-06-08 Maksym Andriushchenko , Francesco Croce , Maximilian Müller , Matthias Hein , Nicolas Flammarion

Learning in Deep Neural Networks (DNN) takes place by minimizing a non-convex high-dimensional loss function, typically by a stochastic gradient descent (SGD) strategy. The learning process is observed to be able to find good minimizers…

Machine Learning · Computer Science 2020-03-12 Carlo Baldassi , Fabrizio Pittorino , Riccardo Zecchina

We propose a novel federated learning method for distributively training neural network models, where the server orchestrates cooperation between a subset of randomly chosen devices in each round. We view Federated Learning problem…