{"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/adaptive-teachers-for-amortized-samplers","title":"Adaptive teachers for amortized samplers","arxiv_id":"2410.01432","date":"2024-10-02","proceeding":null,"authors":["Minsu Kim","Sanghyeok Choi","Taeyoung Yun","Emmanuel Bengio","Leo Feng","Jarrid Rector-Brooks","Sungsoo Ahn","Jinkyoo Park","Nikolay Malkin","Yoshua Bengio"],"abstract":"Amortized inference is the task of training a parametric model, such as a neural network, to approximate a distribution with a given unnormalized density where exact sampling is intractable. When sampling is implemented as a sequential decision-making process, reinforcement learning (RL) methods, such as generative flow networks, can be used to train the sampling policy. Off-policy RL training facilitates the discovery of diverse, high-reward candidates, but existing methods still face challenges in efficient exploration. We propose to use an adaptive training distribution (the \\teacher) to guide the training of the primary amortized sampler (the \\student). The \\teacher, an auxiliary behavior model, is trained to sample high-loss regions of the \\student and can generalize across unexplored modes, thereby enhancing mode coverage by providing an efficient training curriculum. We validate the effectiveness of this approach in a synthetic environment designed to present an exploration challenge, two diffusion-based sampling tasks, and four biochemical discovery tasks demonstrating its ability to improve sample efficiency and mode coverage. Source code is available at https://github.com/alstn12088/adaptive-teacher.","url_abs":"https://arxiv.org/abs/2410.01432v2","url_pdf":"https://arxiv.org/pdf/2410.01432v2.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":"adaptive-teachers-for-amortized-samplers","repo_url":"https://github.com/alstn12088/adaptive-teacher","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"efficient-exploration","task_name":"Efficient Exploration"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"sequential-decision-making","task_name":"Sequential Decision Making"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.01432","atlas_url":"https://app.syntology.ai/?focus=2410.01432","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01432"}},"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":"deterministic:regex_extraction","url":"https://github.com/alstn12088/adaptive-teacher","reach":null}],"summary":{"ran":1,"ran_draft_wrong":2,"ran_fixture":1,"ran_honours":1},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":5,"samples":[{"code_sha256_prefix":"ad1d91a903c30ac7","entry":"TeacherGFlowNet","repo":"alstn12088/adaptive-teacher","repo_kind":"official","path":"discovery/gflownet/GFNs/teacher.py","file_url":"https://github.com/alstn12088/adaptive-teacher/blob/HEAD/discovery/gflownet/GFNs/teacher.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ad1d91a903c30ac7"}},{"code_sha256_prefix":"830498975b1eccbb","entry":"accumulate_by_traj","repo":"alstn12088/adaptive-teacher","repo_kind":"official","path":"discovery/gflownet/GFNs/teacher.py","file_url":"https://github.com/alstn12088/adaptive-teacher/blob/HEAD/discovery/gflownet/GFNs/teacher.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"830498975b1eccbb"}},{"code_sha256_prefix":"1a1ebe33ee0285e0","entry":"batch","repo":"alstn12088/adaptive-teacher","repo_kind":"official","path":"discovery/gflownet/GFNs/teacher.py","file_url":"https://github.com/alstn12088/adaptive-teacher/blob/HEAD/discovery/gflownet/GFNs/teacher.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1a1ebe33ee0285e0"}},{"code_sha256_prefix":"973c7b0697f6a623","entry":"tensor_to_np","repo":"alstn12088/adaptive-teacher","repo_kind":"official","path":"discovery/gflownet/GFNs/teacher.py","file_url":"https://github.com/alstn12088/adaptive-teacher/blob/HEAD/discovery/gflownet/GFNs/teacher.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"973c7b0697f6a623"}},{"code_sha256_prefix":"9d260f82cae9af81","entry":"unroll_trajs","repo":"alstn12088/adaptive-teacher","repo_kind":"official","path":"discovery/gflownet/GFNs/teacher.py","file_url":"https://github.com/alstn12088/adaptive-teacher/blob/HEAD/discovery/gflownet/GFNs/teacher.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9d260f82cae9af81"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}