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 / 547 papers shown

Title
Walking on the Fiber: A Simple Geometric Approximation for Bayesian Neural Networks Alfredo Reichlin Miguel Vasco Danica Kragic BDL UQCV 148 0 0 01 Dec 2025
Merge and Bound: Direct Manipulations on Weights for Class Incremental Learning Taehoon Kim Donghwan Jang Bohyung Han CLL MoMe 185 0 0 26 Nov 2025
A Systematic Study of Model Merging Techniques in Large Language Models Oğuz Kağan Hitit Leander Girrbach Zeynep Akata MoMe 249 0 0 26 Nov 2025
Merging without Forgetting: Continual Fusion of Task-Specific Models via Optimal Transport Z. Pan Zhikang Chen Ding Li Min Zhang Sen Cui ... Yi Yang Deheng Ye Yu Zhang T. Zhu Tianling Ren MoMe CLL FedML 275 0 0 24 Nov 2025
Subtract the Corruption: Training-Data-Free Corrective Machine Unlearning using Task Arithmetic Mostafa Mozafari F. Wani Maria Sofia Bucarelli Fabrizio Silvestri 124 0 0 24 Nov 2025
Shadows in the Code: Exploring the Risks and Defenses of LLM-based Multi-Agent Software Development Systems Xiaoqing Wang Keman Huang Bin Liang Hongyu Li Xiaoyong Du LLMAG AAML 168 0 0 23 Nov 2025
Escaping Optimization Stagnation: Taking Steps Beyond Task Arithmetic via Difference Vectors Jinping Wang Zhiqiang Gao Dinggen Zhang Zhiwu Xie MoMe 216 0 0 22 Nov 2025
Symmetry-Aware Graph Metanetwork Autoencoders: Model Merging through Parameter Canonicalization Odysseas Boufalis Jorge Carrasco-Pollo Joshua Rosenthal Eduardo Terres-Caballero Alejandro García-Castellanos 117 0 0 16 Nov 2025
Uncertainty-Guided Selective Adaptation Enables Cross-Platform Predictive Fluorescence Microscopy Kai-Wen K. Yang Andrew Bai Alexandra Bermudez Yunqi Hong Zoe Latham Iris Sloan Michael Liu Vishrut Goyal Cho-Jui Hsieh Neil Y. C. Lin OOD MedIm 194 0 0 15 Nov 2025
Adaptive Stepsizing for Stochastic Gradient Langevin Dynamics in Bayesian Neural Networks Rajit Rajpal Benedict Leimkuhler Yuanhao Jiang BDL 383 0 0 11 Nov 2025
Model Merging Improves Zero-Shot Generalization in Bioacoustic Foundation Models Davide Marincione Donato Crisostomi Roberto Dessi Emanuele Rodolà Emanuele Rossi MoMe AI4CE VLM 299 1 0 07 Nov 2025
Linear Mode Connectivity under Data Shifts for Deep Ensembles of Image Classifiers C. Hepburn T. Zielke A.P. Raulf 143 0 0 06 Nov 2025
Sharp Minima Can Generalize: A Loss Landscape Perspective On Data Raymond Fan Bryce Sandlund Lin Myat Ko 80 0 0 06 Nov 2025
Shared Parameter Subspaces and Cross-Task Linearity in Emergently Misaligned Behavior Daniel Aarao Reis Arturi Eric Zhang Andrew Ansah Kevin Zhu Ashwinee Panda Aishwarya Balwani 65 0 0 03 Nov 2025
Keys in the Weights: Transformer Authentication Using Model-Bound Latent Representations Ayşe S. Okatan Mustafa İlhan Akbaş Laxima Niure Kandel Berker Peköz 112 0 0 02 Nov 2025
WeaveRec: An LLM-Based Cross-Domain Sequential Recommendation Framework with Model Merging Min Hou Xin Liu Le Wu Chenyi He Hao Liu Z. Li Xin Li Si Wei MoMe 257 0 0 30 Oct 2025
Parameter Averaging in Link Prediction Rupesh Sapkota Caglar Demir Arnab Sharma A. Ngomo MoMe FedML 264 0 0 29 Oct 2025
A Unified Perspective on Optimization in Machine Learning and Neuroscience: From Gradient Descent to Neural Adaptation Jesus Garcia Fernandez Nasir Ahmad Marcel van Gerven AI4CE 225 0 0 21 Oct 2025
Closing the Curvature Gap: Full Transformer Hessians and Their Implications for Scaling Laws Egor Petrov Nikita Kiselev Vladislav Meshkov Andrey Grabovoy 89 0 0 19 Oct 2025
MIN-Merging: Merge the Important Neurons for Model Merging Yunfei Liang MoMe 485 0 0 18 Oct 2025
REAP the Experts: Why Pruning Prevails for One-Shot MoE compression Mike Lasby Ivan Lazarevich Nish Sinnadurai Sean Lie Yani Andrew Ioannou Vithursan Thangarasa 96 1 0 15 Oct 2025
Understanding the Effects of Domain Finetuning on LLMs Eshaan Tanwar Deepak Nathani William Yang Wang Tanmoy Chakraborty 104 0 0 10 Oct 2025
Do We Really Need Permutations? Impact of Width Expansion on Linear Mode Connectivity Akira Ito Masanori Yamada Daiki Chijiwa Atsutoshi Kumagai MoMe 173 0 0 09 Oct 2025
Gradient-Sign Masking for Task Vector Transport Across Pre-Trained Models Filippo Rinaldi Aniello Panariello Giacomo Salici Fengyuan Liu Marco Ciccone Angelo Porrello Simone Calderara 167 0 0 07 Oct 2025
Improving Clinical Dataset Condensation with Mode Connectivity-based Trajectory Surrogates Pafue Christy Nganjimi A. Soltan Danielle Belgrave Lei A. Clifton David Clifton A. Thakur DD AI4CE 204 0 0 07 Oct 2025
How does the optimizer implicitly bias the model merging loss landscape? Chenxiang Zhang Alexander Theus Damien Teney Antonio Orvieto Jun Pang S. Mauw MoMe 174 1 0 06 Oct 2025
Categorical Invariants of Learning Dynamics Abdulrahman Tamim OOD 101 0 0 05 Oct 2025
Non-Linear Trajectory Modeling for Multi-Step Gradient Inversion Attacks in Federated Learning Li Xia Zheng Liu Sili Huang Wei Tang Xuan Liu Xuan Liu AAML 108 1 0 26 Sep 2025
Closing the Oracle Gap: Increment Vector Transformation for Class Incremental Learning Zihuan Qiu Yi Xu Fanman Meng Runtong Zhang Linfeng XU Qingbo Wu Hongliang Li CLL VLM 125 0 0 26 Sep 2025
The Thinking Spectrum: An Empirical Study of Tunable Reasoning in LLMs through Model Merging Xiaochong Lan Yu Zheng Shiteng Cao Yong Li MoMe LRM 183 0 0 26 Sep 2025
Sharpness-Aware Minimization Can Hallucinate Minimizers Chanwoong Park Uijeong Jang Ernest K. Ryu Insoon Yang 95 0 0 26 Sep 2025
Pre-training under infinite compute Konwoo Kim Suhas Kotha Abigail Z. Jacobs Tatsunori Hashimoto 200 1 0 18 Sep 2025
Exploring the Relationship between Brain Hemisphere States and Frequency Bands through Deep Learning Optimization Techniques Robiul Islam Dmitry I. Ignatov Karl Kaberg Roman Nabatchikov 97 0 0 17 Sep 2025
Harnessing Optimization Dynamics for Curvature-Informed Model Merging Pouria Mahdavinia Hamed Mahdavi Niloofar Mireshghallah M. Mahdavi MoMe 167 1 0 14 Sep 2025
Characterizing Fitness Landscape Structures in Prompt Engineering Arend Hintze 84 0 0 04 Sep 2025
Distribution Shift Aware Neural Tabular Learning Wangyang Ying Nanxu Gong Dongjie Wang Xinyuan Wang Arun Vignesh Malarkkan Vivek Gupta Chandan K. Reddy Yanjie Fu OOD 198 3 0 27 Aug 2025
Learning from Oblivion: Predicting Knowledge Overflowed Weights via Retrodiction of Forgetting Jinhyeok Jang Jaehong Kim Jung Uk Kim 72 0 0 07 Aug 2025
Forgetting of task-specific knowledge in model merging-based continual learning Timm Hess Gido M. van de Ven Tinne Tuytelaars CLL FedML MoMe KELM VLM 158 0 0 31 Jul 2025
Feel-Good Thompson Sampling for Contextual Bandits: a Markov Chain Monte Carlo Showdown Emile Anand Sarah Liaw 208 0 0 21 Jul 2025
On the Surprising Effectiveness of a Single Global Merging in Decentralized Learning Tongtian Zhu Tianyu Zhang Mingze Wang Zhanpeng Zhou Can Wang FedML MoMe 288 0 0 09 Jul 2025
Generalized Linear Mode Connectivity for Transformers Alexander Theus Alessandro Cabodi Sotiris Anagnostidis Antonio Orvieto Sidak Pal Singh Valentina Boeva 221 1 0 28 Jun 2025
Subspace-Boosted Model Merging Ronald Skorobogat Karsten Roth Mariana-Iuliana Georgescu MoMe 367 2 0 19 Jun 2025
Flat Channels to Infinity in Neural Loss Landscapes Flavio Martinelli Alexander Van Meegen Berfin Simsek W. Gerstner Johanni Brea 253 2 0 17 Jun 2025
The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions Devin Kwok Gül Sena Altıntaş Colin Raffel David Rolnick 331 2 0 16 Jun 2025
Symmetry in Neural Network Parameter Spaces Bo Zhao Robin Walters Rose Yu 317 6 0 16 Jun 2025
Circumventing Backdoor Space via Weight Symmetry Jie Peng Hongwei Yang Jing Zhao Hengji Dong Hui He Weizhe Zhang Haoyu He AAML 192 0 0 09 Jun 2025
Decom-Renorm-Merge: Model Merging on the Right Space Improves Multitasking Yuatyong Chaichana Thanapat Trachu Peerat Limkonchotiwat Konpat Preechakul Tirasan Khandhawit Ekapol Chuangsuwanich MoMe 529 0 0 29 May 2025
Understanding Mode Connectivity via Parameter Space Symmetry B. Zhao Nima Dehmamy Robin Walters Rose Yu 501 10 0 29 May 2025
SGD as Free Energy Minimization: A Thermodynamic View on Neural Network Training Ildus Sadrtdinov Ivan Klimov E. Lobacheva Dmitry Vetrov 176 1 0 29 May 2025
Benignity of loss landscape with weight decay requires both large overparametrization and initialization Etienne Boursier Matthew Bowditch Matthias Englert R. Lazic 152 0 0 28 May 2025