{"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/evidential-softmax-for-sparse-multimodal","title":"Evidential Softmax for Sparse Multimodal Distributions in Deep Generative Models","arxiv_id":"2110.14182","date":"2021-10-27","proceeding":"NeurIPS 2021 12","authors":["Phil Chen","Masha Itkina","Ransalu Senanayake","Mykel J. Kochenderfer"],"abstract":"Many applications of generative models rely on the marginalization of their high-dimensional output probability distributions. Normalization functions that yield sparse probability distributions can make exact marginalization more computationally tractable. However, sparse normalization functions usually require alternative loss functions for training since the log-likelihood is undefined for sparse probability distributions. Furthermore, many sparse normalization functions often collapse the multimodality of distributions. In this work, we present $\\textit{ev-softmax}$, a sparse normalization function that preserves the multimodality of probability distributions. We derive its properties, including its gradient in closed-form, and introduce a continuous family of approximations to $\\textit{ev-softmax}$ that have full support and can be trained with probabilistic loss functions such as negative log-likelihood and Kullback-Leibler divergence. We evaluate our method on a variety of generative models, including variational autoencoders and auto-regressive architectures. Our method outperforms existing dense and sparse normalization techniques in distributional accuracy. We demonstrate that $\\textit{ev-softmax}$ successfully reduces the dimensionality of probability distributions while maintaining multimodality.","url_abs":"https://arxiv.org/abs/2110.14182v1","url_pdf":"https://arxiv.org/pdf/2110.14182v1.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":[{"paper_slug":"evidential-softmax-for-sparse-multimodal","repo_url":"https://github.com/sisl/evsoftmax","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.14182","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.14182"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/ritheshkumar95/pytorch-vqvae","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sisl/evsoftmax","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1}},"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":"55a0d28cac6c28d4","entry":"evsoftmax","repo":"sisl/evsoftmax","repo_kind":"official","path":"evsoftmax.py","file_url":"https://github.com/sisl/evsoftmax/blob/HEAD/evsoftmax.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"55a0d28cac6c28d4"}},{"code_sha256_prefix":"902209933e7fa0d6","entry":"evsoftmax_loss","repo":"sisl/evsoftmax","repo_kind":"official","path":"evsoftmax.py","file_url":"https://github.com/sisl/evsoftmax/blob/HEAD/evsoftmax.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"902209933e7fa0d6"}},{"code_sha256_prefix":"04bc269c9b4d72fe","entry":"log_evsoftmax","repo":"sisl/evsoftmax","repo_kind":"official","path":"evsoftmax.py","file_url":"https://github.com/sisl/evsoftmax/blob/HEAD/evsoftmax.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"04bc269c9b4d72fe"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}