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
On original and latent space connectivity in deep neural networks Boyang Gu Anastasia Borovykh GNN 3DPC 150 1 0 12 Nov 2023
From Charts to Atlas: Merging Latent Spaces into One Donato Crisostomi Irene Cannistraci Luca Moschella Pietro Barbiero Marco Ciccone Pietro Lio Emanuele Rodolà 176 4 0 11 Nov 2023
Two Complementary Perspectives to Continual Learning: Ask Not Only What to Optimize, But Also How Timm Hess Tinne Tuytelaars Gido M. van de Ven 187 11 0 08 Nov 2023
Analysis of NaN Divergence in Training Monocular Depth Estimation Model Bum Jun Kim Hyeonah Jang Sang Woo Kim 153 0 0 07 Nov 2023
Proving Linear Mode Connectivity of Neural Networks via Optimal TransportInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2023 Damien Ferbach Baptiste Goujaud Gauthier Gidel Hadrien Hendrikx MoMe 357 17 0 29 Oct 2023
Linear Mode Connectivity in Sparse Neural Networks Luke McDermott Daniel Cummings 114 2 0 28 Oct 2023
Improving generalization in large language models by learning prefix subspacesConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 Louis Falissard Vincent Guigue Laure Soulier 75 2 0 24 Oct 2023
A Quadratic Synchronization Rule for Distributed Deep LearningInternational Conference on Learning Representations (ICLR), 2023 Xinran Gu Kaifeng Lyu Sanjeev Arora Jingzhao Zhang Longbo Huang 243 4 0 22 Oct 2023
Revisiting Deep Ensemble for Out-of-Distribution Detection: A Loss Landscape PerspectiveInternational Journal of Computer Vision (IJCV), 2023 Kun Fang Qinghua Tao Xiaolin Huang Jie Yang OODD 193 6 0 22 Oct 2023
Equivariant Deep Weight Space Alignment Aviv Navon Aviv Shamsian Ethan Fetaya Gal Chechik Nadav Dym Haggai Maron 319 29 0 20 Oct 2023
Relearning Forgotten Knowledge: on Forgetting, Overfit and Training-Free Ensembles of DNNs Uri Stern D. Weinshall CLL 177 0 0 17 Oct 2023
Domain Generalization Using Large Pretrained Models with Mixture-of-AdaptersIEEE Workshop/Winter Conference on Applications of Computer Vision (WACV), 2023 Gyuseong Lee Wooseok Jang Jin Hyeon Kim Jaewoo Jung Seungryong Kim MoE OOD 168 9 0 17 Oct 2023
On permutation symmetries in Bayesian neural network posteriors: a variational perspectiveNeural Information Processing Systems (NeurIPS), 2023 Simone Rossi Ankit Singh T. Hannagan 203 3 0 16 Oct 2023
A Symmetry-Aware Exploration of Bayesian Neural Network PosteriorsInternational Conference on Learning Representations (ICLR), 2023 Olivier Laurent Emanuel Aldea Gianni Franchi BDL UQCV 243 10 0 12 Oct 2023
Going Beyond Neural Network Feature Similarity: The Network Feature Complexity and Its Interpretation Using Category TheoryInternational Conference on Learning Representations (ICLR), 2023 Yiting Chen Zhanpeng Zhou Junchi Yan 236 10 0 10 Oct 2023
Transformer Fusion with Optimal TransportInternational Conference on Learning Representations (ICLR), 2023 Moritz Imfeld Jacopo Graldi Marco Giordano Thomas Hofmann Sotiris Anagnostidis Sidak Pal Singh ViT MoMe 406 28 0 09 Oct 2023
Parameter Efficient Multi-task Model Fusion with Partial LinearizationInternational Conference on Learning Representations (ICLR), 2023 Anke Tang Li Shen Yong Luo Yibing Zhan Han Hu Bo Du Yixin Chen Dacheng Tao MoMe 295 49 0 07 Oct 2023
Window-based Model Averaging Improves Generalization in Heterogeneous Federated Learning Debora Caldarola Barbara Caputo Marco Ciccone FedML 226 8 0 02 Oct 2023
Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing PolicyInternational Conference on Learning Representations (ICLR), 2023 Pingzhi Li Zhenyu Zhang Prateek Yadav Yi-Lin Sung Yu Cheng Mohit Bansal Tianlong Chen MoMe 218 71 0 02 Oct 2023
Towards guarantees for parameter isolation in continual learning Giulia Lanzillotta Sidak Pal Singh Benjamin Grewe Thomas Hofmann 194 0 0 02 Oct 2023
RRR-Net: Reusing, Reducing, and Recycling a Deep Backbone NetworkIEEE International Joint Conference on Neural Network (IJCNN), 2023 Haozhe Sun Isabelle M Guyon F. Mohr Hedi Tabia CVBM 156 3 0 02 Oct 2023
Mode Connectivity and Data Heterogeneity of Federated Learning Tailin Zhou Jun Zhang Danny H. K. Tsang FedML 206 4 0 29 Sep 2023
A Primer on Bayesian Neural Networks: Review and Debates Federico Danieli Konstantinos Pitas M. Vladimirova Vincent Fortuin BDL AAML 223 34 0 28 Sep 2023
Deep Model Fusion: A Survey Weishi Li Yong Peng Miao Zhang Liang Ding Han Hu Li Shen FedML MoMe 257 85 0 27 Sep 2023
Neuro-Visualizer: An Auto-encoder-based Loss Landscape Visualization Method Mohannad Elhamod Anuj Karpatne 157 3 0 26 Sep 2023
Policy Optimization in a Noisy Neighborhood: On Return Landscapes in Continuous ControlNeural Information Processing Systems (NeurIPS), 2023 Nate Rahn P. DÓro Harley Wiltzer Pierre-Luc Bacon Marc G. Bellemare 204 6 0 26 Sep 2023
Improve Deep Forest with Learnable Layerwise Augmentation Policy ScheduleIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023 Hongyu Zhu Sichu Liang Wentao Hu Fangqi Li Yali Yuan Shi-Lin Wang Guang Cheng 110 3 0 16 Sep 2023
Geodesic Mode Connectivity Charlie Tan Theodore Long Sarah Zhao Rudolf Laine 151 3 0 24 Aug 2023
Mode Combinability: Exploring Convex Combinations of Permutation Aligned ModelsNeural Networks (Neural Netw.), 2023 Adrián Csiszárik M. Kiss Péter Korösi-Szabó Márton Muntag Gergely Papp D. Varga MoMe 150 1 0 22 Aug 2023
Learning to Generate Training Datasets for Robust Semantic SegmentationIEEE Workshop/Winter Conference on Applications of Computer Vision (WACV), 2023 Marwane Hariat Olivier Laurent Rémi Kazmierczak Shihao Zhang Andrei Bursuc Angela Yao Gianni Franchi UQCV 187 2 0 01 Aug 2023
Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature ConnectivityNeural Information Processing Systems (NeurIPS), 2023 Zhanpeng Zhou Yongyi Yang Xiaojiang Yang Junchi Yan Wei Hu 246 45 0 17 Jul 2023
Tangent Model Composition for Ensembling and Continual Fine-tuningIEEE International Conference on Computer Vision (ICCV), 2023 Tianlin Liu Stefano Soatto LRM MoMe CLL 189 23 0 16 Jul 2023
Layer-wise Linear Mode ConnectivityInternational Conference on Learning Representations (ICLR), 2023 Linara Adilova Maksym Andriushchenko Michael Kamp Asja Fischer Martin Jaggi FedML FAtt MoMe 425 20 0 13 Jul 2023
On The Impact of Machine Learning Randomness on Group FairnessConference on Fairness, Accountability and Transparency (FAccT), 2023 Prakhar Ganesh Hong Chang Martin Strobel Reza Shokri FaML 200 36 0 09 Jul 2023
Minimum Levels of Interpretability for Artificial Moral AgentsAI and Ethics (AE), 2023 Avish Vijayaraghavan C. Badea AI4CE 143 6 0 02 Jul 2023
Sparse Model Soups: A Recipe for Improved Pruning via Model AveragingInternational Conference on Learning Representations (ICLR), 2023 Max Zimmer Christoph Spiegel Sebastian Pokutta MoMe 423 18 0 29 Jun 2023
Black holes and the loss landscape in machine learningJournal of High Energy Physics (JHEP), 2023 P. Kumar Taniya Mandal Swapnamay Mondal 171 2 0 26 Jun 2023
The Inductive Bias of Flatness Regularization for Deep Matrix Factorization Khashayar Gatmiry Zhiyuan Li Ching-Yao Chuang Sashank J. Reddi Tengyu Ma Stefanie Jegelka ODL 172 13 0 22 Jun 2023
No Wrong Turns: The Simple Geometry Of Neural Networks Optimization PathsInternational Conference on Machine Learning (ICML), 2023 Charles Guille-Escuret Hiroki Naganuma Kilian Fatras Ioannis Mitliagkas 146 6 0 20 Jun 2023
Traversing Between Modes in Function Space for Fast EnsemblingInternational Conference on Machine Learning (ICML), 2023 Eunggu Yun Hyungi Lee G. Nam Juho Lee UQCV 135 3 0 20 Jun 2023
Collapsed Inference for Bayesian Deep LearningNeural Information Processing Systems (NeurIPS), 2023 Zhe Zeng Karen Ullrich FedML BDL UQCV 280 11 0 16 Jun 2023
Lookaround Optimizer: $k$ steps around, 1 step averageNeural Information Processing Systems (NeurIPS), 2023 Jiangtao Zhang Shunyu Liu Mingli Song Tongtian Zhu Zhenxing Xu Weilong Dai MoMe 366 8 0 13 Jun 2023
Consistent Explanations in the Face of Model Indeterminacy via Ensembling Dan Ley Leonard Tang Matthew Nazari Hongjin Lin Suraj Srinivas Himabindu Lakkaraju 182 2 0 09 Jun 2023
Optimal Transport Model Distributional RobustnessNeural Information Processing Systems (NeurIPS), 2023 Van-Anh Nguyen Trung Le Anh Tuan Bui Thanh-Toan Do Dinh Q. Phung OOD 217 4 0 07 Jun 2023
TIES-Merging: Resolving Interference When Merging ModelsNeural Information Processing Systems (NeurIPS), 2023 Prateek Yadav Derek Tam Leshem Choshen Colin Raffel Joey Tianyi Zhou MoMe 362 499 0 02 Jun 2023
Optimal Sets and Solution Paths of ReLU NetworksInternational Conference on Machine Learning (ICML), 2023 Aaron Mishkin Mert Pilanci 302 5 0 31 May 2023
A Rainbow in Deep Network Black Boxes Florentin Guth Brice Ménard G. Rochette S. Mallat 295 19 0 29 May 2023
A Three-regime Model of Network PruningInternational Conference on Machine Learning (ICML), 2023 Yefan Zhou Yaoqing Yang Arin Chang Michael W. Mahoney 201 13 0 28 May 2023
Domain Aligned Prefix Averaging for Domain Generalization in Abstractive SummarizationAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 Pranav Ajit Nair Sukomal Pal Pradeepika Verm MoMe 192 2 0 26 May 2023
How to escape sharp minima with random perturbationsInternational Conference on Machine Learning (ICML), 2023 Kwangjun Ahn Ali Jadbabaie S. Sra ODL 336 12 0 25 May 2023

All Papers

Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs

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