v1v2v3v4 (latest)

Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs

Neural Information Processing Systems (NeurIPS), 2018

27 February 2018

Dmitry Vetrov

Papers citing "Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs"

50 / 546 papers shown

Title
Exploring the Hidden Capacity of LLMs for One-Step Text Generation Gleb Mezentsev Ivan Oseledets 226 0 0 27 May 2025
The Unreasonable Effectiveness of Model Merging for Cross-Lingual Transfer in LLMs Lucas Bandarkar Nanyun Peng MoMe LRM 271 1 0 23 May 2025
Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models Patrick Leask Neel Nanda Noura Al Moubayed 231 1 0 23 May 2025
Unveiling the Basin-Like Loss Landscape in Large Language Models Huanran Chen Yinpeng Dong Zeming Wei Yao Huang Yichi Zhang Hang Su Jun Zhu MoMe 325 5 0 23 May 2025
Semantic Aware Linear Transfer by Recycling Pre-trained Language Models for Cross-lingual TransferAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 Seungyoon Lee Seongtae Hong Hyeonseok Moon Heuiseok Lim KELM 268 1 0 16 May 2025
Connecting Independently Trained Modes via Layer-Wise Connectivity Yongding Tian Zaid Al-Ars Maksim Kitsak P. Hofstee 3DPC 265 1 0 05 May 2025
The effect of the number of parameters and the number of local feature patches on loss landscapes in distributed quantum neural networks Yoshiaki Kawase 197 0 0 27 Apr 2025
Dynamic Fisher-weighted Model Merging via Bayesian OptimizationNorth American Chapter of the Association for Computational Linguistics (NAACL), 2025 Sanwoo Lee Jiahao Liu Qifan Wang Jiadong Wang Xunliang Cai Yunfang Wu MoMe 871 4 0 26 Apr 2025
Seeking Flat Minima over Diverse Surrogates for Improved Adversarial Transferability: A Theoretical Framework and Algorithmic Instantiation Meixi Zheng Kehan Wu Yanbo Fan Rui Huang Baoyuan Wu AAML 191 0 0 23 Apr 2025
A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization Sahil Rajesh Dhayalkar 246 4 0 20 Apr 2025
Boosting-inspired online learning with transfer for railway maintenance Diogo Risca Afonso Lourenço Goreti Marreiros 151 1 0 11 Apr 2025
Understanding Machine Unlearning Through the Lens of Mode Connectivity Jiali Cheng Hadi Amiri MU 876 3 0 08 Apr 2025
MASS: MoErging through Adaptive Subspace Selection Donato Crisostomi Alessandro Zirilli Antonio Andrea Gargiulo Maria Sofia Bucarelli Simone Scardapane Fabrizio Silvestri Iacopo Masi Emanuele Rodolà MoMe 243 0 0 06 Apr 2025
Uncertainty-Aware Decomposed Hybrid Networks Sina Ditzel Achref Jaziri Iuliia Pliushch Visvanathan Ramesh UQCV 230 1 0 24 Mar 2025
Finding Stable Subnetworks at Initialization with Dataset Distillation Luke McDermott Rahul Parhi DD 305 0 0 23 Mar 2025
Adiabatic Fine-Tuning of Neural Quantum States Enables Detection of Phase Transitions in Weight Space Vinicius Hernandes Thomas Spriggs Saqar Khaleefah E. Greplova 301 6 0 21 Mar 2025
Aggregation on Learnable Manifolds for Asynchronous Federated Optimization Archie Licudi A. Thakur Soheila Molaei Danielle Belgrave David Clifton FedML 169 0 0 18 Mar 2025
On Local Posterior Structure in Deep EnsemblesInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2025 Mikkel Jordahn Jonas Vestergaard Jensen Mikkel N. Schmidt Michael Riis Andersen UQCV BDL OOD 306 0 0 17 Mar 2025
Make Optimization Once and for All with Fine-grained Guidance Mingjia Shi Ruihan Lin Xuxi Chen Yuhao Zhou Zezhen Ding ... Tong Wang Xiaojiang Peng Zhangyang Wang Jing Zhang Tianlong Chen 262 1 0 14 Mar 2025
Understanding Flatness in Generative Models: Its Role and Benefits Taehwan Lee Kyeongkook Seo Jaejun Yoo Sung Whan Yoon DiffM 272 1 0 14 Mar 2025
Analyzing the Role of Permutation Invariance in Linear Mode ConnectivityInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2025 Keyao Zhan Puheng Li Lei Wu MoMe 273 1 0 13 Mar 2025
From Task-Specific Models to Unified Systems: A Review of Model Merging Approaches Wei Ruan Tianze Yang Yimiao Zhou Tianming Liu Jin Lu MoMe 321 6 0 13 Mar 2025
Self-Ensembling Gaussian Splatting for Few-Shot Novel View Synthesis Chen Zhao Xuan Wang Tong Zhang Saqib Javed Mathieu Salzmann 3DGS 1.2K 2 0 13 Mar 2025
Task Vector Quantization for Memory-Efficient Model Merging Youngeun Kim Seunghwan Lee Aecheon Jung Bogon Ryu Sungeun Hong MQ MoMe 228 3 0 10 Mar 2025
You Only Debias Once: Towards Flexible Accuracy-Fairness Trade-offs at Inference Time Xiaotian Han Tianlong Chen Kaixiong Zhou Zhimeng Jiang Zhangyang Wang Helen Zhou 773 0 0 10 Mar 2025
SplatPose: Geometry-Aware 6-DoF Pose Estimation from Single RGB Image via 3D Gaussian Splatting Linqi Yang Xiongwei Zhao Qihao Sun Ke Wang Ao Chen Peng Kang 3DGS 283 9 0 07 Mar 2025
Paths and Ambient Spaces in Neural Loss LandscapesInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2025 Daniel Dold Julius Kobialka Nicolai Palm Emanuel Sommer David Rügamer Oliver Durr AI4CE 343 1 0 05 Mar 2025
Deep Learning is Not So Mysterious or Different Andrew Gordon Wilson 281 21 0 03 Mar 2025
Extrapolating and Decoupling Image-to-Video Generation Models: Motion Modeling is Easier Than You ThinkComputer Vision and Pattern Recognition (CVPR), 2025 Jie Tian Xiaoye Qu Zhenyi Lu Xiaoye Qu Sichen Liu Yu Cheng DiffM VGen 170 8 0 02 Mar 2025
Rethinking Spiking Neural Networks from an Ensemble Learning PerspectiveInternational Conference on Learning Representations (ICLR), 2025 Lin Zuo Yongqi Ding Mengmeng Jing Pei He Hanpu Deng 257 10 0 20 Feb 2025
High-dimensional manifold of solutions in neural networks: insights from statistical physics Enrico M. Malatesta 274 5 0 20 Feb 2025
Unveiling Mode Connectivity in Graph Neural Networks Bingheng Li Z. Chen Haoyu Han Shenglai Zeng J. Liu Shucheng Zhou 208 1 0 18 Feb 2025
SuperMerge: An Approach For Gradient-Based Model Merging Haoyu Yang Zheng Zhang Saket Sathe MoMe 335 0 0 17 Feb 2025
LoRE-Merging: Exploring Low-Rank Estimation For Large Language Model Merging Zehua Liu Han Wu Yuxuan Yao Ruifeng She Xiongwei Han Tao Zhong Mingxuan Yuan MoMe 247 4 0 15 Feb 2025
Ensembles of Low-Rank Expert AdaptersInternational Conference on Learning Representations (ICLR), 2025 Yinghao Li Vianne Gao Chao Zhang MohamadAli Torkamani 371 5 0 31 Jan 2025
FedDAG: Federated Domain Adversarial Generation Towards Generalizable Medical Image AnalysisIEEE Transactions on Medical Imaging (IEEE TMI), 2025 Haoxuan Che Yifei Wu Haibo Jin Yong-quan Xia Hao Chen OOD FedML MedIm 81 3 0 28 Jan 2025
CENSOR: Defense Against Gradient Inversion via Orthogonal Subspace Bayesian SamplingNetwork and Distributed System Security Symposium (NDSS), 2025 Kaiyuan Zhang Siyuan Cheng Guangyu Shen Bruno Ribeiro Shengwei An Pin-Yu Chen Xinming Zhang Ninghui Li 646 6 0 28 Jan 2025
Evolutionary Optimization of Physics-Informed Neural Networks: Evo-PINN Frontiers and Opportunities Jian Cheng Wong Abhishek Gupta Chin Chun Ooi P. Chiu Jiao Liu Yew-Soon Ong PINN AI4CE 211 0 0 11 Jan 2025
Parameter-Efficient Interventions for Enhanced Model Merging Marcin Osial Daniel Marczak Bartosz Zieliñski MoMe 322 1 0 22 Dec 2024
Non-Uniform Parameter-Wise Model MergingBigData Congress [Services Society] (BSS), 2024 Albert Manuel Orozco Camacho Stefan Horoi Guy Wolf Eugene Belilovsky MoMe FedML 329 0 0 20 Dec 2024
LossLens: Diagnostics for Machine Learning through Loss Landscape Visual AnalyticsIEEE Computer Graphics and Applications (IEEE CG&A), 2024 Tiankai Xie Jiaqing Chen Yaoqing Yang Caleb Geniesse Ge Shi ... J. Cava Michael W. Mahoney Talita Perciano Gunther H. Weber Ross Maciejewski 195 1 0 17 Dec 2024
Meta Curvature-Aware Minimization for Domain Generalization Zhaoyu Chen Yiwen Ye Feilong Tang Yongsheng Pan Yong-quan Xia BDL 875 1 0 16 Dec 2024
Implicit Neural Compression of Point Clouds Hongning Ruan Yulin Shao Qianqian Yang Liang Zhao Zhaoyang Zhang Dusit Niyato 3DPC 331 1 0 11 Dec 2024
How to Merge Your Multimodal Models Over Time?Computer Vision and Pattern Recognition (CVPR), 2024 Sebastian Dziadzio Vishaal Udandarao Karsten Roth Christian Schroeder de Witt Zeynep Akata Samuel Albanie Matthias Bethge MoMe 358 13 0 09 Dec 2024
Task Arithmetic Through The Lens Of One-Shot Federated Learning Zhixu Tao I. Mason Sanjeev R. Kulkarni Xavier Boix MoMe FedML 405 8 0 27 Nov 2024
FREE-Merging: Fourier Transform for Efficient Model Merging Shenghe Zheng Hongzhi Wang MoMe 272 1 0 25 Nov 2024
Ex Uno Pluria: Insights on Ensembling in Low Precision Number SystemsNeural Information Processing Systems (NeurIPS), 2024 G. Nam Juho Lee 260 1 0 22 Nov 2024
Stein Variational Newton Neural Network Ensembles Klemens Flöge Mohammed Abdul Moeed Vincent Fortuin BDL UQCV 249 0 0 04 Nov 2024
MoD: A Distribution-Based Approach for Merging Large Language Models Quy-Anh Dang Chris Ngo MoMe VLM 177 0 0 01 Nov 2024
TabM: Advancing Tabular Deep Learning with Parameter-Efficient EnsemblingInternational Conference on Learning Representations (ICLR), 2024 Yury Gorishniy Akim Kotelnikov Artem Babenko LMTD MoE 564 38 0 31 Oct 2024