{"work":{"id":"97d95295-30e1-42b4-bbf6-85f0fa4edb44","openalex_id":null,"doi":null,"arxiv_id":"1312.6114","raw_key":null,"title":"Auto-Encoding Variational Bayes","authors":null,"authors_text":"URLhttp://arxiv","year":2013,"venue":"stat.ML","abstract":"How can we perform efficient inference and learning in directed probabilistic models, in the presence of continuous latent variables with intractable posterior distributions, and large datasets? We introduce a stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case. Our contributions are two-fold. First, we show that a reparameterization of the variational lower bound yields a lower bound estimator that can be straightforwardly optimized using standard stochastic gradient methods. Second, we show that for i.i.d. datasets with continuous latent variables per datapoint, posterior inference can be made especially efficient by fitting an approximate inference model (also called a recognition model) to the intractable posterior using the proposed lower bound estimator. Theoretical advantages are reflected in experimental results.","external_url":"https://arxiv.org/abs/1312.6114","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-25T19:51:10.779246+00:00","pith_arxiv_id":"1312.6114","created_at":"2026-05-08T22:34:20.136642+00:00","updated_at":"2026-05-25T19:51:10.779246+00:00","title_quality_ok":true,"display_title":"Auto-Encoding Variational Bayes","render_title":"Auto-Encoding Variational Bayes"},"hub":{"state":{"work_id":"97d95295-30e1-42b4-bbf6-85f0fa4edb44","tier":"super_hub","tier_reason":"100+ Pith inbound or 10,000+ external citations","pith_inbound_count":534,"external_cited_by_count":null,"distinct_field_count":51,"first_pith_cited_at":"2015-11-19T22:50:32+00:00","last_pith_cited_at":"2026-05-22T11:50:40+00:00","author_build_status":"needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-06-02T22:35:14.586442+00:00","tier_text":"super_hub"},"tier":"super_hub","role_counts":[{"context_role":"background","n":72},{"context_role":"method","n":32},{"context_role":"baseline","n":2}],"polarity_counts":[{"context_polarity":"background","n":69},{"context_polarity":"use_method","n":30},{"context_polarity":"unclear","n":4},{"context_polarity":"baseline","n":2},{"context_polarity":"support","n":1}],"runs":{"ask_index":{"job_type":"ask_index","status":"succeeded","result":{"title":"Auto-Encoding Variational Bayes","claims":[{"claim_text":"How can we perform efficient inference and learning in directed probabilistic models, in the presence of continuous latent variables with intractable posterior distributions, and large datasets? We introduce a stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case. Our contributions are two-fold. First, we show that a reparameterization of the variational lower bound yields a lower bound estimator that can be straightforwardly optimized using standard stochastic gradient methods","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Auto-Encoding Variational Bayes because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-13T19:23:29.959209+00:00"},"author_expand":{"job_type":"author_expand","status":"succeeded","result":{"authors_linked":[{"id":"9755edb3-40df-4592-845a-026d5c5037e0","orcid":null,"display_name":"URLhttp://arxiv"}]},"error":null,"updated_at":"2026-05-13T19:23:29.956899+00:00"},"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-13T19:23:29.680886+00:00"},"graph_features":{"job_type":"graph_features","status":"succeeded","result":{"co_cited":[{"title":"Denoising Diffusion Implicit Models","work_id":"8fa2128b-d18c-405c-ac92-0e669cf89ac0","shared_citers":30},{"title":"Adam: A Method for Stochastic Optimization","work_id":"1910796d-9b52-4683-bf5c-de9632c1028b","shared_citers":29},{"title":"Classifier-Free Diffusion Guidance","work_id":"acf2c588-c088-4a6c-938e-150ad7c666d7","shared_citers":29},{"title":"Flow Matching for Generative Modeling","work_id":"6edb71c4-5d64-40af-a394-9757ea051a36","shared_citers":28},{"title":"Decoupled Weight Decay Regularization","work_id":"07ef7360-d385-4033-83f7-8384a6325204","shared_citers":22},{"title":"Score-Based Generative Modeling through Stochastic Differential Equations","work_id":"d9110e53-a5d4-4794-a4c5-a575e91c31ad","shared_citers":19},{"title":"DINOv2: Learning Robust Visual Features without Supervision","work_id":"26b304e5-b54a-4f26-be7e-83299eca52e4","shared_citers":17},{"title":"Wan: Open and Advanced Large-Scale Video Generative Models","work_id":"ad3ebc3b-4224-46c9-b61d-bcf135da0a7c","shared_citers":17},{"title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","work_id":"a1989e1b-d66d-4533-be3a-fb9c5fd62290","shared_citers":16},{"title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","work_id":"0c6a768b-70b8-4242-bb0e-459f1008c9fc","shared_citers":16},{"title":"Proximal Policy Optimization Algorithms","work_id":"240c67fe-d14d-4520-91c1-38a4e272ca19","shared_citers":16},{"title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","work_id":"4f68eada-27e3-437a-a2fe-6e4ca524d0d3","shared_citers":16},{"title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","work_id":"e96730e3-129b-4db6-b981-15ab7932e297","shared_citers":15},{"title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","work_id":"8034c587-fba6-4941-87ba-c98f2ac962cb","shared_citers":14},{"title":"Qwen3-VL Technical Report","work_id":"1fe243aa-e3c0-4da6-b391-4cbcfc88d5c0","shared_citers":12},{"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","shared_citers":11},{"title":"Density estimation using Real NVP","work_id":"d5ef47e5-d72b-4ac0-8a61-b21ebfecf593","shared_citers":10},{"title":"DINOv3","work_id":"c8b07deb-8fe7-4e18-9620-f3569d3529ce","shared_citers":10},{"title":"Gemini: A Family of Highly Capable Multimodal Models","work_id":"83f7c85b-3f11-450f-ac0c-64d9745220b2","shared_citers":10},{"title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","work_id":"34430d19-7919-48ce-88a5-17b3bfe2192e","shared_citers":10},{"title":"Qwen-Image Technical Report","work_id":"d06d7ecc-7579-4f89-a60b-4278a0f3c562","shared_citers":10},{"title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","work_id":"1f9d1d3b-a6d6-45a9-9f13-51393c03be8a","shared_citers":9},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":9},{"title":"LLaMA: Open and Efficient Foundation Language Models","work_id":"c018fc23-6f3f-4035-9d02-28a2173b2b9d","shared_citers":9}],"time_series":[{"n":1,"year":2015},{"n":2,"year":2016},{"n":2,"year":2019},{"n":2,"year":2020},{"n":3,"year":2021},{"n":3,"year":2022},{"n":4,"year":2023},{"n":8,"year":2024},{"n":3,"year":2025},{"n":205,"year":2026}]},"error":null,"updated_at":"2026-05-13T19:23:29.804950+00:00"},"identity_refresh":{"job_type":"identity_refresh","status":"succeeded","result":{"fixed":1,"items":[{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","resolver":"local_arxiv","confidence":0.98,"old_work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e"}],"errors":[],"attempted":1},"error":null,"updated_at":"2026-05-13T19:23:29.001917+00:00"},"role_polarity":{"job_type":"role_polarity","status":"succeeded","result":{"title":"Auto-Encoding Variational Bayes","claims":[{"claim_text":"How can we perform efficient inference and learning in directed probabilistic models, in the presence of continuous latent variables with intractable posterior distributions, and large datasets? We introduce a stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case. Our contributions are two-fold. First, we show that a reparameterization of the variational lower bound yields a lower bound estimator that can be straightforwardly optimized using standard stochastic gradient methods","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Auto-Encoding Variational Bayes because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-13T19:23:29.685828+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"Auto-Encoding Variational Bayes","claims":[{"claim_text":"How can we perform efficient inference and learning in directed probabilistic models, in the presence of continuous latent variables with intractable posterior distributions, and large datasets? We introduce a stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case. Our contributions are two-fold. First, we show that a reparameterization of the variational lower bound yields a lower bound estimator that can be straightforwardly optimized using standard stochastic gradient methods","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Auto-Encoding Variational Bayes because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-13T19:23:29.684016+00:00"}},"summary":{"title":"Auto-Encoding Variational Bayes","claims":[{"claim_text":"How can we perform efficient inference and learning in directed probabilistic models, in the presence of continuous latent variables with intractable posterior distributions, and large datasets? We introduce a stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case. Our contributions are two-fold. First, we show that a reparameterization of the variational lower bound yields a lower bound estimator that can be straightforwardly optimized using standard stochastic gradient methods","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Auto-Encoding Variational Bayes because it crossed a citation-hub threshold.","role_counts":[]},"graph":{"co_cited":[{"title":"Denoising Diffusion Implicit Models","work_id":"8fa2128b-d18c-405c-ac92-0e669cf89ac0","shared_citers":30},{"title":"Adam: A Method for Stochastic Optimization","work_id":"1910796d-9b52-4683-bf5c-de9632c1028b","shared_citers":29},{"title":"Classifier-Free Diffusion Guidance","work_id":"acf2c588-c088-4a6c-938e-150ad7c666d7","shared_citers":29},{"title":"Flow Matching for Generative Modeling","work_id":"6edb71c4-5d64-40af-a394-9757ea051a36","shared_citers":28},{"title":"Decoupled Weight Decay Regularization","work_id":"07ef7360-d385-4033-83f7-8384a6325204","shared_citers":22},{"title":"Score-Based Generative Modeling through Stochastic Differential Equations","work_id":"d9110e53-a5d4-4794-a4c5-a575e91c31ad","shared_citers":19},{"title":"DINOv2: Learning Robust Visual Features without Supervision","work_id":"26b304e5-b54a-4f26-be7e-83299eca52e4","shared_citers":17},{"title":"Wan: Open and Advanced Large-Scale Video Generative Models","work_id":"ad3ebc3b-4224-46c9-b61d-bcf135da0a7c","shared_citers":17},{"title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","work_id":"a1989e1b-d66d-4533-be3a-fb9c5fd62290","shared_citers":16},{"title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","work_id":"0c6a768b-70b8-4242-bb0e-459f1008c9fc","shared_citers":16},{"title":"Proximal Policy Optimization Algorithms","work_id":"240c67fe-d14d-4520-91c1-38a4e272ca19","shared_citers":16},{"title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","work_id":"4f68eada-27e3-437a-a2fe-6e4ca524d0d3","shared_citers":16},{"title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","work_id":"e96730e3-129b-4db6-b981-15ab7932e297","shared_citers":15},{"title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","work_id":"8034c587-fba6-4941-87ba-c98f2ac962cb","shared_citers":14},{"title":"Qwen3-VL Technical Report","work_id":"1fe243aa-e3c0-4da6-b391-4cbcfc88d5c0","shared_citers":12},{"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","shared_citers":11},{"title":"Density estimation using Real NVP","work_id":"d5ef47e5-d72b-4ac0-8a61-b21ebfecf593","shared_citers":10},{"title":"DINOv3","work_id":"c8b07deb-8fe7-4e18-9620-f3569d3529ce","shared_citers":10},{"title":"Gemini: A Family of Highly Capable Multimodal Models","work_id":"83f7c85b-3f11-450f-ac0c-64d9745220b2","shared_citers":10},{"title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","work_id":"34430d19-7919-48ce-88a5-17b3bfe2192e","shared_citers":10},{"title":"Qwen-Image Technical Report","work_id":"d06d7ecc-7579-4f89-a60b-4278a0f3c562","shared_citers":10},{"title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","work_id":"1f9d1d3b-a6d6-45a9-9f13-51393c03be8a","shared_citers":9},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":9},{"title":"LLaMA: Open and Efficient Foundation Language Models","work_id":"c018fc23-6f3f-4035-9d02-28a2173b2b9d","shared_citers":9}],"time_series":[{"n":1,"year":2015},{"n":2,"year":2016},{"n":2,"year":2019},{"n":2,"year":2020},{"n":3,"year":2021},{"n":3,"year":2022},{"n":4,"year":2023},{"n":8,"year":2024},{"n":3,"year":2025},{"n":205,"year":2026}]},"authors":[{"id":"9755edb3-40df-4592-845a-026d5c5037e0","orcid":null,"display_name":"URLhttp://arxiv","source":"manual","import_confidence":0.72}]}}