https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#head https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0 http://www.nanopub.org/nschema#hasAssertion https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#assertion https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0 http://www.nanopub.org/nschema#hasProvenance https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#provenance https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0 http://www.nanopub.org/nschema#hasPublicationInfo https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#pubinfo https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0 http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://www.nanopub.org/nschema#Nanopublication https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#assertion https://arxiv.org/abs/2406.12208 https://sense-nets.xyz/hasZoteroItemType preprint https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#assertion http://purl.org/dc/terms/creator https://w3id.org/np/RAoSadUw99CeqDlR2400018nqTzR_38fT86OrTzk16Vts https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#assertion http://purl.org/spar/cito/discusses https://x.com/LChoshen/status/1729488495515713672 https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#assertion http://purl.org/spar/cito/discusses https://x.com/prateeky2806/status/1665759148380758022 https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#assertion http://purl.org/spar/cito/reviews https://arxiv.org/abs/2406.12208 https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#assertion http://www.w3.org/2000/01/rdf-schema#comment Evolver, model merging in a genetic algorithm Improves on current merging techniques (my beloved TIES 🫣 ) Train diverse models Merge regularly or take diff between two models Update some parameters Keep if good Repeat https://arxiv.org/abs/2406.12208 @jingli9111 @banting_liu @576gsk https://twitter.com/LChoshen/status/1803410440535326786/photo/1 Merging is aimed at taking many models and getting one that generalizes better, there are various methods for it, read more e.g. on TIES https://x.com/prateeky2806/status/1665759148380758022 Genetic algorithms evolve models, in steps: Create mutations (here new m = m_old + a(m_1-m_2)) m are models a some constant Crossover, take some of the mutation and apply it, for each parameter randomly keep m_old or update to m_new Survive, keep only the best performing on val By sometimes merging and sometimes evolving (and dev sets) they improve over all current methods https://twitter.com/LChoshen/status/1803410445635653960/photo/1 In some sense, this can be seen as a better search in the region between the merged models, which we know is not equally good but all better than the edges https://x.com/LChoshen/status/1729488495515713672 https://twitter.com/LChoshen/status/1803410447246250483/photo/1 https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#assertion https://schema.org/keywords TIES https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#assertion https://schema.org/keywords evolver https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#assertion https://schema.org/keywords genetic\_algorithms https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#assertion https://schema.org/keywords knowledge\_fusion https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#assertion https://schema.org/keywords model\_merging https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#assertion https://sense-nets.xyz/endorses https://x.com/LChoshen/status/1729488495515713672 https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#assertion https://sense-nets.xyz/summarizes https://arxiv.org/abs/2406.12208 https://x.com/LChoshen/status/1729488495515713672 https://sense-nets.xyz/hasZoteroItemType forumPost https://x.com/prateeky2806/status/1665759148380758022 https://sense-nets.xyz/hasZoteroItemType forumPost https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#provenance https://sense-nets.xyz/ http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://www.w3.org/ns/prov#SoftwareAgent https://sense-nets.xyz/ http://www.w3.org/ns/prov#actedOnBehalfOf https://w3id.org/np/RAoSadUw99CeqDlR2400018nqTzR_38fT86OrTzk16Vts https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#activity http://www.w3.org/1999/02/22-rdf-syntax-ns#type https://sense-nets.xyz/supervisedActivity https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#activity http://www.w3.org/ns/prov#wasAssociatedWith https://sense-nets.xyz/ https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#assertion http://www.w3.org/ns/prov#linksTo https://x.com/LChoshen/status/1803410440535326786 https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#assertion http://www.w3.org/ns/prov#wasAssociatedWith https://x.com/LChoshen https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#assertion http://www.w3.org/ns/prov#wasAttributedTo https://orcid.org/0000-0002-0085-6496 https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#assertion http://www.w3.org/ns/prov#wasAttributedTo https://w3id.org/np/RAoSadUw99CeqDlR2400018nqTzR_38fT86OrTzk16Vts https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#assertion http://www.w3.org/ns/prov#wasGeneratedBy https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#activity https://w3id.org/np/RAoSadUw99CeqDlR2400018nqTzR_38fT86OrTzk16Vts http://xmlns.com/foaf/0.1/account https://orcid.org/0000-0002-0085-6496 https://w3id.org/np/RAoSadUw99CeqDlR2400018nqTzR_38fT86OrTzk16Vts http://xmlns.com/foaf/0.1/account https://x.com/LChoshen https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#pubinfo https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#sig http://purl.org/nanopub/x/hasAlgorithm RSA https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#sig http://purl.org/nanopub/x/hasPublicKey MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEArHtI92jm8pAYVsvJabxLGfOT+7G0JyJGh2gwjB5x2pFPga6wWTd+rNBWWUZViIFnaJrBEsJpgdnoupLU9ppwn+khMiGRfxqGsDDzwHcj3Jc75CRys7d3etwXdBdoXfBgjsJiZBazwm13idr6tljRrC1TaEJBnRQAqzBw9cLDeGY77cSznzXT39feUGT168dpCSE9O6u/48DvvWVqciHGsH9cQ+LroJJVsMrorwtsdZnAK+q48wtIP6pIpw5shSJ5LnA0qeN/f4TvTFDV6ItYIXjiWWpTECc/Bxmfnyat3B5xWCu9nvz8fEs7Ns0TuzQwT3/K55iSKDEIi/E0nO97xwIDAQAB https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#sig http://purl.org/nanopub/x/hasSignature DNd+uaVNO1EL2UnPQPKV4vb8L7Raa/kQy4vZM/hINGKItf80gXEU92oqDkX0iQjdWVeW1qvhQIneMk0X1opywCbxtOFfqgoWCCApVokDmjuHB9pH+iSMubN4xflRdPg2K6Vypi6WR5l4dU3VvCRRT9BICyzUXNqyca5KDAqtU2gpQOT6qMnQrKpLDev88NeCWI/F/2M9WiNeuLbZvr72bOmEmSgMANu6wZE81vyJjM45lxevTOTviZC74BZdP3RMyaBb7nRlU4Ek8Wazux8Oc4PHzMp0RV/neTirBfA+NLlx0XfWXj+q/jvepqIiSnQdm/jkf4PpZ/N3GLYp4JWyrA== https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#sig http://purl.org/nanopub/x/hasSignatureTarget https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0 https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#sig http://purl.org/nanopub/x/singedBy https://sense-nets.xyz/ https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0#sig http://www.w3.org/ns/prov#wasAssociatedWith https://w3id.org/np/RAoSadUw99CeqDlR2400018nqTzR_38fT86OrTzk16VtssigningDelegation https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0 http://purl.org/dc/terms/created 2024-09-12T18:58:02.418Z https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0 http://purl.org/dc/terms/creator https://w3id.org/np/RAoSadUw99CeqDlR2400018nqTzR_38fT86OrTzk16Vts https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0 http://purl.org/dc/terms/license https://creativecommons.org/licenses/by/4.0/ https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0 http://purl.org/nanopub/x/hasNanopubType https://sense-nets.xyz/SemanticPost https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0 http://purl.org/nanopub/x/wasCreatedAt https://sense-nets.xyz/ https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0 http://www.w3.org/2000/01/rdf-schema#label CoSMO Semantic Post https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0 http://www.w3.org/ns/prov#wasAttributedTo https://orcid.org/0000-0002-0085-6496 https://w3id.org/np/RAKmi8CK-UdWMP9L6Q9YymxVSFsIlM1cP-6WDc4T4ocN0 https://sense-nets.xyz/hasRootSigner 0xf6ECcfD463afB464dcC85b051DF2E93E2646E6D2 https://w3id.org/np/RAoSadUw99CeqDlR2400018nqTzR_38fT86OrTzk16Vts http://xmlns.com/foaf/0.1/account https://orcid.org/0000-0002-0085-6496 https://w3id.org/np/RAoSadUw99CeqDlR2400018nqTzR_38fT86OrTzk16Vts http://xmlns.com/foaf/0.1/name Leshem Choshen 🤖🤗 @ICML wanna talk?