{"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/ladder-variational-autoencoders","title":"Ladder Variational Autoencoders","arxiv_id":"1602.02282","date":"2016-02-06","proceeding":"NeurIPS 2016 12","authors":["Casper Kaae Sønderby","Tapani Raiko","Lars Maaløe","Søren Kaae Sønderby","Ole Winther"],"abstract":"Variational Autoencoders are powerful models for unsupervised learning.\nHowever deep models with several layers of dependent stochastic variables are\ndifficult to train which limits the improvements obtained using these highly\nexpressive models. We propose a new inference model, the Ladder Variational\nAutoencoder, that recursively corrects the generative distribution by a data\ndependent approximate likelihood in a process resembling the recently proposed\nLadder Network. We show that this model provides state of the art predictive\nlog-likelihood and tighter log-likelihood lower bound compared to the purely\nbottom-up inference in layered Variational Autoencoders and other generative\nmodels. We provide a detailed analysis of the learned hierarchical latent\nrepresentation and show that our new inference model is qualitatively different\nand utilizes a deeper more distributed hierarchy of latent variables. Finally,\nwe observe that batch normalization and deterministic warm-up (gradually\nturning on the KL-term) are crucial for training variational models with many\nstochastic layers.","url_abs":"http://arxiv.org/abs/1602.02282v3","url_pdf":"http://arxiv.org/pdf/1602.02282v3.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":"ladder-variational-autoencoders","repo_url":"https://github.com/casperkaae/LVAE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"ladder-variational-autoencoders","repo_url":"https://github.com/Leozyc-waseda/DeepLearning_Course_Homework","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"ladder-variational-autoencoders","repo_url":"https://github.com/divymurli/VAEs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"ladder-variational-autoencoders","repo_url":"https://github.com/simonamtoft/ml-library","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"ladder-variational-autoencoders","repo_url":"https://github.com/addtt/ladder-vae-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"unsupervised-mnist","task_name":"Unsupervised MNIST"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"hierarchical-vae","method_name":"Hierarchical VAE"}],"datasets_introduced":[],"methods_introduced":[{"slug":"hierarchical-vae","name":"Hierarchical VAE","full_name":"Hierarchical Variational Autoencoder"}],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1602.02282","atlas_url":"https://app.syntology.ai/?focus=1602.02282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1602.02282"}},"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/simonamtoft/ml-library","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/casperkaae/LVAE","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/divymurli/VAEs","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Leozyc-waseda/DeepLearning_Course_Homework","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/addtt/ladder-vae-pytorch","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":2,"ran":1,"unverified":6},"by_repo_kind":{"listed":{"samples":9,"ran":3,"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":"ff92ad8f00e93bbc","entry":"IOU","repo":"Leozyc-waseda/DeepLearning_Course_Homework","repo_kind":"listed","path":"gen_anchors.py","file_url":"https://github.com/Leozyc-waseda/DeepLearning_Course_Homework/blob/HEAD/gen_anchors.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ff92ad8f00e93bbc"}},{"code_sha256_prefix":"1a3fa3dda9a8b100","entry":"avg_IOU","repo":"Leozyc-waseda/DeepLearning_Course_Homework","repo_kind":"listed","path":"gen_anchors.py","file_url":"https://github.com/Leozyc-waseda/DeepLearning_Course_Homework/blob/HEAD/gen_anchors.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1a3fa3dda9a8b100"}},{"code_sha256_prefix":"04bbdadb21f8b94d","entry":"convert","repo":"Leozyc-waseda/DeepLearning_Course_Homework","repo_kind":"listed","path":"gen_files.py","file_url":"https://github.com/Leozyc-waseda/DeepLearning_Course_Homework/blob/HEAD/gen_files.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":"04bbdadb21f8b94d"}},{"code_sha256_prefix":"02f3a50faf2e52a3","entry":"discretized_mix_logistic_loss","repo":"addtt/ladder-vae-pytorch","repo_kind":"listed","path":"lib/likelihoods.py","file_url":"https://github.com/addtt/ladder-vae-pytorch/blob/HEAD/lib/likelihoods.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":"02f3a50faf2e52a3"}},{"code_sha256_prefix":"1ab085dba2b341ea","entry":"kl_normal_mc","repo":"addtt/ladder-vae-pytorch","repo_kind":"listed","path":"lib/stochastic.py","file_url":"https://github.com/addtt/ladder-vae-pytorch/blob/HEAD/lib/stochastic.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":"1ab085dba2b341ea"}},{"code_sha256_prefix":"84eb98948d67591f","entry":"log_bernoulli","repo":"addtt/ladder-vae-pytorch","repo_kind":"listed","path":"lib/likelihoods.py","file_url":"https://github.com/addtt/ladder-vae-pytorch/blob/HEAD/lib/likelihoods.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":"84eb98948d67591f"}},{"code_sha256_prefix":"fabc798a2d64531f","entry":"log_discretized_logistic","repo":"addtt/ladder-vae-pytorch","repo_kind":"listed","path":"lib/likelihoods.py","file_url":"https://github.com/addtt/ladder-vae-pytorch/blob/HEAD/lib/likelihoods.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":"fabc798a2d64531f"}},{"code_sha256_prefix":"4686a937eb425646","entry":"logistic_rsample","repo":"addtt/ladder-vae-pytorch","repo_kind":"listed","path":"lib/stochastic.py","file_url":"https://github.com/addtt/ladder-vae-pytorch/blob/HEAD/lib/stochastic.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":"4686a937eb425646"}},{"code_sha256_prefix":"be3871d2562a0801","entry":"sample_from_discretized_mix_logistic","repo":"addtt/ladder-vae-pytorch","repo_kind":"listed","path":"lib/stochastic.py","file_url":"https://github.com/addtt/ladder-vae-pytorch/blob/HEAD/lib/stochastic.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":"be3871d2562a0801"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}