{"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/balancing-reconstruction-error-and-kullback","title":"Balancing reconstruction error and Kullback-Leibler divergence in Variational Autoencoders","arxiv_id":"2002.07514","date":"2020-02-18","proceeding":null,"authors":["Andrea Asperti","Matteo Trentin"],"abstract":"In the loss function of Variational Autoencoders there is a well known tension between two components: the reconstruction loss, improving the quality of the resulting images, and the Kullback-Leibler divergence, acting as a regularizer of the latent space. Correctly balancing these two components is a delicate issue, easily resulting in poor generative behaviours. In a recent work, Dai and Wipf obtained a sensible improvement by allowing the network to learn the balancing factor during training, according to a suitable loss function. In this article, we show that learning can be replaced by a simple deterministic computation, helping to understand the underlying mechanism, and resulting in a faster and more accurate behaviour. On typical datasets such as Cifar and Celeba, our technique sensibly outperforms all previous VAE architectures.","url_abs":"https://arxiv.org/abs/2002.07514v1","url_pdf":"https://arxiv.org/pdf/2002.07514v1.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":"balancing-reconstruction-error-and-kullback","repo_url":"https://github.com/asperti/BalancingVAE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"balancing-reconstruction-error-and-kullback","repo_url":"https://github.com/lovelyscientist/rna-seq-vae","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2002.07514","atlas_url":"https://app.syntology.ai/?focus=2002.07514","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.07514"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/asperti/BalancingVAE","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lovelyscientist/rna-seq-vae","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":3,"ran":2,"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":1,"samples":[{"code_sha256_prefix":"f5002f45f9802d08","entry":"get_expressions","repo":"lovelyscientist/rna-seq-vae","repo_kind":"listed","path":"gtex_loader.py","file_url":"https://github.com/lovelyscientist/rna-seq-vae/blob/HEAD/gtex_loader.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":"f5002f45f9802d08"}},{"code_sha256_prefix":"a5ea53bdbdb19025","entry":"idx2onehot","repo":"lovelyscientist/rna-seq-vae","repo_kind":"listed","path":"torch_model.py","file_url":"https://github.com/lovelyscientist/rna-seq-vae/blob/HEAD/torch_model.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a5ea53bdbdb19025"}},{"code_sha256_prefix":"38ed4e3667407885","entry":"unpickle","repo":"asperti/BalancingVAE","repo_kind":"official","path":"computed_gamma.py","file_url":"https://github.com/asperti/BalancingVAE/blob/HEAD/computed_gamma.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"38ed4e3667407885"}},{"code_sha256_prefix":"42e0c9a532dc4421","entry":"get_samples","repo":"lovelyscientist/rna-seq-vae","repo_kind":"listed","path":"gtex_loader.py","file_url":"https://github.com/lovelyscientist/rna-seq-vae/blob/HEAD/gtex_loader.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":"42e0c9a532dc4421"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}