{"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/streamlining-prediction-in-bayesian-deep","title":"Streamlining Prediction in Bayesian Deep Learning","arxiv_id":"2411.18425","date":"2024-11-27","proceeding":null,"authors":["Rui Li","Marcus Klasson","Arno Solin","Martin Trapp"],"abstract":"The rising interest in Bayesian deep learning (BDL) has led to a plethora of methods for estimating the posterior distribution. However, efficient computation of inferences, such as predictions, has been largely overlooked with Monte Carlo integration remaining the standard. In this work we examine streamlining prediction in BDL through a single forward pass without sampling. For this we use local linearisation on activation functions and local Gaussian approximations at linear layers. Thus allowing us to analytically compute an approximation to the posterior predictive distribution. We showcase our approach for both MLP and transformers, such as ViT and GPT-2, and assess its performance on regression and classification tasks. Open-source library: https://github.com/AaltoML/SUQ","url_abs":"https://arxiv.org/abs/2411.18425v3","url_pdf":"https://arxiv.org/pdf/2411.18425v3.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":"streamlining-prediction-in-bayesian-deep","repo_url":"https://github.com/aaltoml/suq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"prediction","task_name":"Prediction"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"discriminative-fine-tuning","method_name":"Discriminative Fine-Tuning"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-2","method_name":"GPT-2"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.18425","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.18425"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aaltoml/suq","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":10},"by_repo_kind":{"official":{"samples":10,"ran":0,"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":"b7495d2791bf5bbc","entry":"forward_aW_diag","repo":"aaltoml/suq","repo_kind":"official","path":"suq/diag_suq_mlp.py","file_url":"https://github.com/aaltoml/suq/blob/HEAD/suq/diag_suq_mlp.py","link_basis":"first_harvest_node","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":"b7495d2791bf5bbc"}},{"code_sha256_prefix":"a0a7b4a473187555","entry":"forward_aW_kron","repo":"aaltoml/suq","repo_kind":"official","path":"suq/kron_suq_mlp.py","file_url":"https://github.com/aaltoml/suq/blob/HEAD/suq/kron_suq_mlp.py","link_basis":"first_harvest_node","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":"a0a7b4a473187555"}},{"code_sha256_prefix":"086ba259d151663b","entry":"forward_activation_diag","repo":"aaltoml/suq","repo_kind":"official","path":"suq/diag_suq_transformer.py","file_url":"https://github.com/aaltoml/suq/blob/HEAD/suq/diag_suq_transformer.py","link_basis":"first_harvest_node","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":"086ba259d151663b"}},{"code_sha256_prefix":"8d0ae8eebf8d786b","entry":"forward_activation_implicit_diag","repo":"aaltoml/suq","repo_kind":"official","path":"suq/diag_suq_mlp.py","file_url":"https://github.com/aaltoml/suq/blob/HEAD/suq/diag_suq_mlp.py","link_basis":"first_harvest_node","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":"8d0ae8eebf8d786b"}},{"code_sha256_prefix":"621f1d22899ef0ce","entry":"forward_activation_implicit_full","repo":"aaltoml/suq","repo_kind":"official","path":"suq/kron_suq_mlp.py","file_url":"https://github.com/aaltoml/suq/blob/HEAD/suq/kron_suq_mlp.py","link_basis":"first_harvest_node","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":"621f1d22899ef0ce"}},{"code_sha256_prefix":"cf6ab4f51928d340","entry":"forward_batch_norm_diag","repo":"aaltoml/suq","repo_kind":"official","path":"suq/diag_suq_mlp.py","file_url":"https://github.com/aaltoml/suq/blob/HEAD/suq/diag_suq_mlp.py","link_basis":"first_harvest_node","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":"cf6ab4f51928d340"}},{"code_sha256_prefix":"1c271f27a5e3dc41","entry":"forward_linear_diag_Bayesian_weight","repo":"aaltoml/suq","repo_kind":"official","path":"suq/diag_suq_transformer.py","file_url":"https://github.com/aaltoml/suq/blob/HEAD/suq/diag_suq_transformer.py","link_basis":"first_harvest_node","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":"1c271f27a5e3dc41"}},{"code_sha256_prefix":"1e9f98732d611733","entry":"forward_linear_diag_determinstic_weight","repo":"aaltoml/suq","repo_kind":"official","path":"suq/diag_suq_transformer.py","file_url":"https://github.com/aaltoml/suq/blob/HEAD/suq/diag_suq_transformer.py","link_basis":"first_harvest_node","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":"1e9f98732d611733"}},{"code_sha256_prefix":"2b1aadd648250de3","entry":"streamline_mlp","repo":"aaltoml/suq","repo_kind":"official","path":"suq/SUQ_MLP.py","file_url":"https://github.com/aaltoml/suq/blob/HEAD/suq/SUQ_MLP.py","link_basis":"first_harvest_node","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":"2b1aadd648250de3"}},{"code_sha256_prefix":"6f1a2485f8616e61","entry":"streamline_vit","repo":"aaltoml/suq","repo_kind":"official","path":"suq/SUQ_ViT.py","file_url":"https://github.com/aaltoml/suq/blob/HEAD/suq/SUQ_ViT.py","link_basis":"first_harvest_node","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":"6f1a2485f8616e61"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}