{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/learnable-polynomial-trigonometric-and","title":"Polynomial, trigonometric, and tropical activations","arxiv_id":"2502.01247","date":"2025-02-03","proceeding":null,"authors":["Ismail Khalfaoui-Hassani","Stefan Kesselheim"],"abstract":"Which functions can be used as activations in deep neural networks? This article explores families of functions based on orthonormal bases, including the Hermite polynomial basis and the Fourier trigonometric basis, as well as a basis resulting from the tropicalization of a polynomial basis. Our study shows that, through simple variance-preserving initialization and without additional clamping mechanisms, these activations can successfully be used to train deep models, such as GPT-2 for next-token prediction on OpenWebText and ConvNeXt for image classification on ImageNet. Our work addresses the issue of exploding and vanishing activations and gradients, particularly prevalent with polynomial activations, and opens the door for improving the efficiency of large-scale learning tasks. Furthermore, our approach provides insight into the structure of neural networks, revealing that networks with polynomial activations can be interpreted as multivariate polynomial mappings. Finally, using Hermite interpolation, we show that our activations can closely approximate classical ones in pre-trained models by matching both the function and its derivative, making them especially useful for fine-tuning tasks. These activations are available in the torchortho library, which can be accessed via: https://github.com/K-H-Ismail/torchortho.","url_abs":"https://arxiv.org/abs/2502.01247v2","url_pdf":"https://arxiv.org/pdf/2502.01247v2.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":"learnable-polynomial-trigonometric-and","repo_url":"https://github.com/K-H-Ismail/torchortho","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"image-classification","task_name":"image-classification"}],"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":"convnext","method_name":"ConvNeXt"},{"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":"hermite","method_name":"Hermite Activation"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":null,"method_name":"Library"},{"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":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ConvNeXt-T-Hermite","rank_in_archive_order":547,"of":1060,"metrics":{"Number of params":"28M","Top 1 Accuracy":"82.34","Top 5 Accuracy":"96.03"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-openwebtext","task":"Language Modelling","dataset":"OpenWebText","model":"GPT2-Hermite","rank_in_archive_order":4,"of":12,"metrics":{"eval_loss":"2.91","eval_perplexity":"18.39","parameters":"124M"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-openwebtext","task":"Language Modelling","dataset":"OpenWebText","model":"GPT2-Tropical","rank_in_archive_order":5,"of":12,"metrics":{"eval_loss":"2.92","eval_perplexity":"18.64","parameters":"124M"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-openwebtext","task":"Language Modelling","dataset":"OpenWebText","model":"GPT2-Fourier","rank_in_archive_order":6,"of":12,"metrics":{"eval_loss":"2.93","eval_perplexity":"18.72","parameters":"124M"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-openwebtext","task":"Language Modelling","dataset":"OpenWebText","model":"GPT2-GELU","rank_in_archive_order":7,"of":12,"metrics":{"eval_loss":"2.95","eval_perplexity":"19.24","parameters":"124M"},"uses_additional_data":false},{"leaderboard":"/sota/text-generation-on-openwebtext","task":"Text Generation","dataset":"OpenWebText","model":"GPT2-Hermite","rank_in_archive_order":1,"of":3,"metrics":{"eval_loss":"2.91"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2502.01247","atlas_url":"https://app.syntology.ai/?focus=2502.01247","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2502.01247"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2502.01247\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2502.01247"},"call":"get_concepts_for_paper(arxiv_id=\"2502.01247\")"}],"by_repo":[{"repo":"K-H-Ismail/torchortho","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"aedb2b2ceabe2a68676c83fc9212e5a94793ac60dfe6b1c17ed130f7ae6e3489","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}