English
Related papers

Related papers: Mechanistic Mode Connectivity

200 papers

We examine how recently documented, fundamental phenomena in deep learning models subject to pruning are affected by changes in the pruning procedure. Specifically, we analyze differences in the connectivity structure and learning dynamics…

Machine Learning · Computer Science 2020-01-16 Michela Paganini , Jessica Forde

Many image processing tasks involve image-to-image mapping, which can be addressed well by fully convolutional networks (FCN) without any heavy preprocessing. Although empirically designing and training FCNs can achieve satisfactory…

Machine Learning · Computer Science 2019-01-25 Jianjie Lu , Kai-yu Tong

This paper presents Bundle Network, a learning-based algorithm inspired by the Bundle Method for convex non-smooth minimization problems. Unlike classical approaches that rely on heuristic tuning of a regularization parameter, our method…

Optimization and Control · Mathematics 2025-09-30 Francesca Demelas , Joseph Le Roux , Antonio Frangioni , Mathieu Lacroix , Emiliano Traversi , Roberto Wolfler Calvo

Structured pruning compresses neural networks by reducing channels (filters) for fast inference and low footprint at run-time. To restore accuracy after pruning, fine-tuning is usually applied to pruned networks. However, too few remaining…

Computer Vision and Pattern Recognition · Computer Science 2024-01-01 Yu Qian , Jian Cao , Xiaoshuang Li , Jie Zhang , Hufei Li , Jue Chen

Multi-fidelity machine learning methods address the accuracy-efficiency trade-off by integrating scarce, resource-intensive high-fidelity data with abundant but less accurate low-fidelity data. We propose a practical multi-fidelity strategy…

Machine Learning · Computer Science 2025-03-26 Jiaxiang Yi , Ji Cheng , Miguel A. Bessa

Cross-domain few-shot learning (CDFSL) aims to acquire knowledge from limited training data in the target domain by leveraging prior knowledge transferred from source domains with abundant training samples. CDFSL faces challenges in…

Computer Vision and Pattern Recognition · Computer Science 2024-04-22 Yixiong Zou , Yicong Liu , Yiman Hu , Yuhua Li , Ruixuan Li

It has been observed that representations learned by distinct neural networks conceal structural similarities when the models are trained under similar inductive biases. From a geometric perspective, identifying the classes of…

Machine Learning · Computer Science 2024-03-21 Irene Cannistraci , Luca Moschella , Marco Fumero , Valentino Maiorca , Emanuele Rodolà

Variational Bayesian posterior inference often requires simplifying approximations such as mean-field parametrisation to ensure tractability. However, prior work has associated the variational mean-field approximation for Bayesian neural…

Machine Learning · Computer Science 2022-10-07 Richard Kurle , Ralf Herbrich , Tim Januschowski , Yuyang Wang , Jan Gasthaus

In a series of recent theoretical works, it was shown that strongly over-parameterized neural networks trained with gradient-based methods could converge exponentially fast to zero training loss, with their parameters hardly varying. In…

Optimization and Control · Mathematics 2020-01-08 Lenaic Chizat , Edouard Oyallon , Francis Bach

Many algorithms and observed phenomena in deep learning appear to be affected by parameter symmetries -- transformations of neural network parameters that do not change the underlying neural network function. These include linear mode…

Machine Learning · Computer Science 2024-10-16 Derek Lim , Theo Moe Putterman , Robin Walters , Haggai Maron , Stefanie Jegelka

In few-shot classification tasks (so-called episodes), a small set of labeled support samples is provided during inference to aid the classification of unlabeled query samples. Metric-based models typically operate by computing similarities…

Machine Learning · Computer Science 2025-06-24 Xuanyu Zhuang , Geoffroy Peeters , Gaël Richard

Single-model ensembles (SMEs) have attracted attention as a way to approximate some of the benefits of deep ensembles within a single network. However, under an approximately matched parameter budget, it remains unclear whether model…

Machine Learning · Computer Science 2026-05-13 Tatsuhito Hasegawa , Taisei Tanaka

It has been shown that instead of learning actual object features, deep networks tend to exploit non-robust (spurious) discriminative features that are shared between training and test sets. Therefore, while they achieve state of the art…

Machine Learning · Statistics 2019-11-19 Devansh Arpit , Caiming Xiong , Richard Socher

Few-shot fine-tuning and in-context learning are two alternative strategies for task adaptation of pre-trained language models. Recently, in-context learning has gained popularity over fine-tuning due to its simplicity and improved…

Computation and Language · Computer Science 2023-05-31 Marius Mosbach , Tiago Pimentel , Shauli Ravfogel , Dietrich Klakow , Yanai Elazar

Fine-tuning is a popular way of exploiting knowledge contained in a pre-trained convolutional network for a new visual recognition task. However, the orthogonal setting of transferring knowledge from a pretrained network to a visually…

Computer Vision and Pattern Recognition · Computer Science 2020-08-28 Amelie Royer , Christoph H. Lampert

The elusive nature of gradient-based optimization in neural networks is tied to their loss landscape geometry, which is poorly understood. However recent work has brought solid evidence that there is essentially no loss barrier between the…

Machine Learning · Statistics 2023-10-17 Simone Rossi , Ankit Singh , Thomas Hannagan

Thesedays, Convolutional Neural Networks are widely used in semantic segmentation. However, since CNN-based segmentation networks produce low-resolution outputs with rich semantic information, it is inevitable that spatial details (e.g.,…

Computer Vision and Pattern Recognition · Computer Science 2019-10-03 Youngeun Kim , Seunghyeon Kim , Taekyung Kim , Changick Kim

Physical and functional constraints on biological networks lead to complex topological patterns across multiple scales in their organization. A particular type of higher-order network feature that has received considerable interest is…

Quantitative Methods · Quantitative Biology 2024-10-15 Alexis Bénichou , Jean-Baptiste Masson , Christian L. Vestergaard

Modern statistical machine translation (SMT) systems usually use a linear combination of features to model the quality of each translation hypothesis. The linear combination assumes that all the features are in a linear relationship and…

Computation and Language · Computer Science 2015-03-03 Shujian Huang , Huadong Chen , Xinyu Dai , Jiajun Chen

Learning maps between data samples is fundamental. Applications range from representation learning, image translation and generative modeling, to the estimation of spatial deformations. Such maps relate feature vectors, or map between…

Computer Vision and Pattern Recognition · Computer Science 2021-06-18 Hastings Greer , Roland Kwitt , Francois-Xavier Vialard , Marc Niethammer