{"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/online-limited-memory-neural-linear-bandits-1","title":"Online Limited Memory Neural-Linear Bandits with Likelihood Matching","arxiv_id":"2102.03799","date":"2021-02-07","proceeding":null,"authors":["Ofir Nabati","Tom Zahavy","Shie Mannor"],"abstract":"We study neural-linear bandits for solving problems where {\\em both} exploration and representation learning play an important role. Neural-linear bandits harnesses the representation power of Deep Neural Networks (DNNs) and combines it with efficient exploration mechanisms by leveraging uncertainty estimation of the model, designed for linear contextual bandits on top of the last hidden layer. In order to mitigate the problem of representation change during the process, new uncertainty estimations are computed using stored data from an unlimited buffer. Nevertheless, when the amount of stored data is limited, a phenomenon called catastrophic forgetting emerges. To alleviate this, we propose a likelihood matching algorithm that is resilient to catastrophic forgetting and is completely online. We applied our algorithm, Limited Memory Neural-Linear with Likelihood Matching (NeuralLinear-LiM2) on a variety of datasets and observed that our algorithm achieves comparable performance to the unlimited memory approach while exhibits resilience to catastrophic forgetting.","url_abs":"https://arxiv.org/abs/2102.03799v2","url_pdf":"https://arxiv.org/pdf/2102.03799v2.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":"online-limited-memory-neural-linear-bandits-1","repo_url":"https://github.com/mlisicki/neuralkernelbandits","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"online-limited-memory-neural-linear-bandits-1","repo_url":"https://github.com/ofirnabati/neural-linear-bandits-with-likelihood-matching","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"online-limited-memory-neural-linear-bandits-1","repo_url":"https://github.com/vectorinstitute/neuralkernelbandits","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"efficient-exploration","task_name":"Efficient Exploration"},{"task_slug":"multi-armed-bandits","task_name":"Multi-Armed Bandits"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2102.03799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.03799"}},"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/vectorinstitute/neuralkernelbandits","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ofirnabati/neural-linear-bandits-with-likelihood-matching","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mlisicki/neuralkernelbandits","reach":null}],"summary":{"ran":1,"unverified":5},"by_repo_kind":{"listed":{"samples":6,"ran":1,"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":"c7065b8e8d0fc36a","entry":"BayesianNN","repo":"mlisicki/neuralkernelbandits","repo_kind":"listed","path":"bandits/algorithms/neural_linear_sampling_lm.py","file_url":"https://github.com/mlisicki/neuralkernelbandits/blob/HEAD/bandits/algorithms/neural_linear_sampling_lm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c7065b8e8d0fc36a"}},{"code_sha256_prefix":"d0408a1c20ece8cd","entry":"BanditAlgorithm","repo":"mlisicki/neuralkernelbandits","repo_kind":"listed","path":"bandits/algorithms/neural_linear_sampling_lm.py","file_url":"https://github.com/mlisicki/neuralkernelbandits/blob/HEAD/bandits/algorithms/neural_linear_sampling_lm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d0408a1c20ece8cd"}},{"code_sha256_prefix":"d9aaab78f5111242","entry":"ContextualDataset","repo":"mlisicki/neuralkernelbandits","repo_kind":"listed","path":"bandits/algorithms/neural_linear_sampling_lm.py","file_url":"https://github.com/mlisicki/neuralkernelbandits/blob/HEAD/bandits/algorithms/neural_linear_sampling_lm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d9aaab78f5111242"}},{"code_sha256_prefix":"b4e47c429a062363","entry":"NeuralBanditModel","repo":"mlisicki/neuralkernelbandits","repo_kind":"listed","path":"bandits/algorithms/neural_linear_sampling_lm.py","file_url":"https://github.com/mlisicki/neuralkernelbandits/blob/HEAD/bandits/algorithms/neural_linear_sampling_lm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b4e47c429a062363"}},{"code_sha256_prefix":"cbd307f86b6e77be","entry":"NeuralLinearPosteriorSamplingLM","repo":"mlisicki/neuralkernelbandits","repo_kind":"listed","path":"bandits/algorithms/neural_linear_sampling_lm.py","file_url":"https://github.com/mlisicki/neuralkernelbandits/blob/HEAD/bandits/algorithms/neural_linear_sampling_lm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cbd307f86b6e77be"}},{"code_sha256_prefix":"c90ccbc7b6fbcb15","entry":"TextCNN","repo":"mlisicki/neuralkernelbandits","repo_kind":"listed","path":"bandits/algorithms/neural_linear_sampling_lm.py","file_url":"https://github.com/mlisicki/neuralkernelbandits/blob/HEAD/bandits/algorithms/neural_linear_sampling_lm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c90ccbc7b6fbcb15"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}