{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/low-loss-space-in-neural-networks-is","title":"Low-Loss Space in Neural Networks is Continuous and Fully Connected","arxiv_id":"2505.02604","date":"2025-05-05","proceeding":null,"authors":["Yongding Tian","Zaid Al-Ars","Maksim Kitsak","Peter Hofstee"],"abstract":"Visualizations of the loss landscape in neural networks suggest that minima are isolated points. However, both theoretical and empirical studies indicate that it is possible to connect two different minima with a path consisting of intermediate points that also have low loss. In this study, we propose a new algorithm which investigates low-loss paths in the full parameter space, not only between two minima. Our experiments on LeNet5, ResNet18, and Compact Convolutional Transformer architectures consistently demonstrate the existence of such continuous paths in the parameter space. These results suggest that the low-loss region is a fully connected and continuous space in the parameter space. Our findings provide theoretical insight into neural network over-parameterization, highlighting that parameters collectively define a high-dimensional low-loss space, implying parameter redundancy exists only within individual models and not throughout the entire low-loss space. Additionally, our work also provides new visualization methods and opportunities to improve model generalization by exploring the low-loss space that is closer to the origin.","url_abs":"https://arxiv.org/abs/2505.02604v1","url_pdf":"https://arxiv.org/pdf/2505.02604v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2505.02604","atlas_url":"https://app.syntology.ai/?focus=2505.02604","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.02604"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/timgaripov/dnn-mode-connectivity","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/fdraxler/PyTorch-AutoNEB","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":8,"unverified":5},"by_repo_kind":{"found_in_text":{"samples":13,"ran":8,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"b86c230cd7b58813","entry":"CurveNet","repo":"timgaripov/dnn-mode-connectivity","repo_kind":"found_in_text","path":"curves.py","file_url":"https://github.com/timgaripov/dnn-mode-connectivity/blob/HEAD/curves.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"b86c230cd7b58813"}},{"code_sha256_prefix":"7d32f814be36436b","entry":"disconnected","repo":"fdraxler/PyTorch-AutoNEB","repo_kind":"found_in_text","path":"torch_autoneb/suggest.py","file_url":"https://github.com/fdraxler/PyTorch-AutoNEB/blob/HEAD/torch_autoneb/suggest.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7d32f814be36436b"}},{"code_sha256_prefix":"f548c84db1ea697f","entry":"distribute_by_weights","repo":"fdraxler/PyTorch-AutoNEB","repo_kind":"found_in_text","path":"torch_autoneb/neb_model.py","file_url":"https://github.com/fdraxler/PyTorch-AutoNEB/blob/HEAD/torch_autoneb/neb_model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f548c84db1ea697f"}},{"code_sha256_prefix":"19a46625e3b4e045","entry":"equal","repo":"fdraxler/PyTorch-AutoNEB","repo_kind":"found_in_text","path":"torch_autoneb/fill.py","file_url":"https://github.com/fdraxler/PyTorch-AutoNEB/blob/HEAD/torch_autoneb/fill.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"19a46625e3b4e045"}},{"code_sha256_prefix":"3a5f3fe91d1517b4","entry":"leave","repo":"fdraxler/PyTorch-AutoNEB","repo_kind":"found_in_text","path":"torch_autoneb/fill.py","file_url":"https://github.com/fdraxler/PyTorch-AutoNEB/blob/HEAD/torch_autoneb/fill.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3a5f3fe91d1517b4"}},{"code_sha256_prefix":"cb7d54d7bc7e17f4","entry":"move_to","repo":"fdraxler/PyTorch-AutoNEB","repo_kind":"found_in_text","path":"torch_autoneb/helpers.py","file_url":"https://github.com/fdraxler/PyTorch-AutoNEB/blob/HEAD/torch_autoneb/helpers.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cb7d54d7bc7e17f4"}},{"code_sha256_prefix":"a1bc3b1cf779ef89","entry":"replace_instanciation","repo":"fdraxler/PyTorch-AutoNEB","repo_kind":"found_in_text","path":"torch_autoneb/config.py","file_url":"https://github.com/fdraxler/PyTorch-AutoNEB/blob/HEAD/torch_autoneb/config.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a1bc3b1cf779ef89"}},{"code_sha256_prefix":"71460029b4fd6d96","entry":"unfinished","repo":"fdraxler/PyTorch-AutoNEB","repo_kind":"found_in_text","path":"torch_autoneb/suggest.py","file_url":"https://github.com/fdraxler/PyTorch-AutoNEB/blob/HEAD/torch_autoneb/suggest.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"71460029b4fd6d96"}},{"code_sha256_prefix":"229f80d59b6789a0","entry":"CurveModule","repo":"timgaripov/dnn-mode-connectivity","repo_kind":"found_in_text","path":"curves.py","file_url":"https://github.com/timgaripov/dnn-mode-connectivity/blob/HEAD/curves.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"229f80d59b6789a0"}},{"code_sha256_prefix":"bde80d96c1e287d8","entry":"conv3x3","repo":"fdraxler/PyTorch-AutoNEB","repo_kind":"found_in_text","path":"torch_autoneb/models/resnet.py","file_url":"https://github.com/fdraxler/PyTorch-AutoNEB/blob/HEAD/torch_autoneb/models/resnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bde80d96c1e287d8"}},{"code_sha256_prefix":"5587b8aa28fe33b6","entry":"highest","repo":"fdraxler/PyTorch-AutoNEB","repo_kind":"found_in_text","path":"torch_autoneb/fill.py","file_url":"https://github.com/fdraxler/PyTorch-AutoNEB/blob/HEAD/torch_autoneb/fill.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5587b8aa28fe33b6"}},{"code_sha256_prefix":"4682f3f06b3460cc","entry":"load_dataset","repo":"fdraxler/PyTorch-AutoNEB","repo_kind":"found_in_text","path":"torch_autoneb/datasets.py","file_url":"https://github.com/fdraxler/PyTorch-AutoNEB/blob/HEAD/torch_autoneb/datasets.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4682f3f06b3460cc"}},{"code_sha256_prefix":"0a98cc5f44b9de32","entry":"ntuple","repo":"fdraxler/PyTorch-AutoNEB","repo_kind":"found_in_text","path":"torch_autoneb/helpers.py","file_url":"https://github.com/fdraxler/PyTorch-AutoNEB/blob/HEAD/torch_autoneb/helpers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0a98cc5f44b9de32"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}