English
Related papers

Related papers: Generalized Linear Mode Connectivity for Transform…

200 papers

The presence of linear paths in parameter space between two different network solutions in certain cases, i.e., linear mode connectivity (LMC), has garnered interest from both theoretical and practical fronts. There has been significant…

Machine Learning · Computer Science 2024-06-25 Sidak Pal Singh , Linara Adilova , Michael Kamp , Asja Fischer , Bernhard Schölkopf , Thomas Hofmann

Linear Mode Connectivity (LMC) refers to the phenomenon that performance remains consistent for linearly interpolated models in the parameter space. For independently optimized model pairs from different random initializations, achieving…

Machine Learning · Computer Science 2025-02-17 Ryuichi Kanoh , Mahito Sugiyama

The phenomenon of linear mode connectivity (LMC) links several aspects of deep learning, including training stability under noisy stochastic gradients, the smoothness and generalization of local minima (basins), the similarity and…

Machine Learning · Computer Science 2025-11-07 C. Hepburn , T. Zielke , A. P. Raulf

Recent work has revealed many intriguing empirical phenomena in neural network training, despite the poorly understood and highly complex loss landscapes and training dynamics. One of these phenomena, Linear Mode Connectivity (LMC), has…

Machine Learning · Computer Science 2023-11-14 Zhanpeng Zhou , Yongyi Yang , Xiaojiang Yang , Junchi Yan , Wei Hu

The loss landscapes of deep neural networks are not well understood due to their high nonconvexity. Empirically, the local minima of these loss functions can be connected by a learned curve in model space, along which the loss remains…

Machine Learning · Computer Science 2020-12-11 N. Joseph Tatro , Pin-Yu Chen , Payel Das , Igor Melnyk , Prasanna Sattigeri , Rongjie Lai

A fundamental challenge in understanding graph neural networks (GNNs) lies in characterizing their optimization dynamics and loss landscape geometry, critical for improving interpretability and robustness. While mode connectivity, a lens…

Machine Learning · Computer Science 2025-02-19 Bingheng Li , Zhikai Chen , Haoyu Han , Shenglai Zeng , Jingzhe Liu , Jiliang Tang

We extend the concept of loss landscape mode connectivity to the input space of deep neural networks. Mode connectivity was originally studied within parameter space, where it describes the existence of low-loss paths between different…

Machine Learning · Computer Science 2024-09-10 Jakub Vrabel , Ori Shem-Ur , Yaron Oz , David Krueger

Linear mode-connectivity (LMC) (or lack thereof) is one of the intriguing characteristics of neural network loss landscapes. While empirically well established, it unfortunately still lacks a proper theoretical understanding. Even worse,…

Machine Learning · Computer Science 2023-12-18 Gul Sena Altintas , Gregor Bachmann , Lorenzo Noci , Thomas Hofmann

Recently, Ainsworth et al. empirically demonstrated that, given two independently trained models, applying a parameter permutation that preserves the input-output behavior allows the two models to be connected by a low-loss linear path.…

Machine Learning · Computer Science 2026-03-09 Akira Ito , Masanori Yamada , Daiki Chijiwa , Atsutoshi Kumagai

We survey the model merging literature through the lens of loss landscape geometry to connect observations from empirical studies on model merging and loss landscape analysis to phenomena that govern neural network training and the…

Neural networks typically exhibit permutation symmetries which contribute to the non-convexity of the networks' loss landscapes, since linearly interpolating between two permuted versions of a trained network tends to encounter a high loss…

Machine Learning · Computer Science 2024-04-10 Ekansh Sharma , Devin Kwok , Tom Denton , Daniel M. Roy , David Rolnick , Gintare Karolina Dziugaite

The success of deep learning is due in large part to our ability to solve certain massive non-convex optimization problems with relative ease. Though non-convex optimization is NP-hard, simple algorithms -- often variants of stochastic…

Machine Learning · Computer Science 2023-03-03 Samuel K. Ainsworth , Jonathan Hayase , Siddhartha Srinivasa

It was empirically observed in Entezari et al. (2021) that when accounting for the permutation invariance of neural networks, there is likely no loss barrier along the linear interpolation between two SGD solutions -- a phenomenon known as…

Machine Learning · Statistics 2025-03-13 Keyao Zhan , Puheng Li , Lei Wu

Deep learning models have proven enormously successful at using multiple layers of representation to learn relevant features of structured data. Encoding physical symmetries into these models can improve performance on difficult tasks, and…

Machine Learning · Computer Science 2025-10-21 Cassidy Ashworth , Pietro Liò , Francesco Caso

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

We develop a geometric account of sequence modelling that links patterns in the data to measurable properties of the loss landscape in transformer networks. First, we cast conditional sequence distributions into a Hilbert-space framework…

Machine Learning · Computer Science 2025-04-28 Zhongtian Chen , Daniel Murfet

We study how permutation symmetries in overparameterized multi-layer neural networks generate `symmetry-induced' critical points. Assuming a network with $ L $ layers of minimal widths $ r_1^*, \ldots, r_{L-1}^* $ reaches a zero-loss…

Machine Learning · Computer Science 2021-09-14 Berfin Şimşek , François Ged , Arthur Jacot , Francesco Spadaro , Clément Hongler , Wulfram Gerstner , Johanni Brea

There are many surprising and perhaps counter-intuitive properties of optimization of deep neural networks. We propose and experimentally verify a unified phenomenological model of the loss landscape that incorporates many of them. High…

Machine Learning · Computer Science 2019-06-12 Stanislav Fort , Stanislaw Jastrzebski

Equivariant neural networks have proven to be effective for tasks with known underlying symmetries. However, optimizing equivariant networks can be tricky and best training practices are less established than for standard networks. In…

Machine Learning · Computer Science 2025-11-04 YuQing Xie , Tess Smidt

It is widely accepted in the mode connectivity literature that when two neural networks are trained similarly on the same data, they are connected by a path through parameter space over which test set accuracy is maintained. Under some…

Machine Learning · Computer Science 2023-01-24 Jeevesh Juneja , Rachit Bansal , Kyunghyun Cho , João Sedoc , Naomi Saphra
‹ Prev 1 2 3 10 Next ›