Reparameterized LLM Training via Orthogonal Equivalence Transformation

Zeju Qiu, Simon Buchholz, Tim Z. Xiao, Maximilian Dax, Bernhard Schölkopf, Weiyang Liu

Reparameterized LLM Training via Orthogonal Equivalence Transformation: 6 upvotes on Hugging Face Daily Papers, #21 of 28 papers on 2025-06-12. Day-by-day upvote history.

While large language models (LLMs) are driving the rapid advancement of artificial intelligence, effectively and reliably training these large models remains one of the field's most significant challenges. To address this challenge, we propose POET, a novel reParameterized training algorithm that uses Orthogonal Equivalence Transformation to optimize neurons. Specifically, POET reparameterizes each neuron with two learnable orthogonal matrices and a fixed random weight matrix. Because of its provable preservation of spectral properties of weight matrices, POET can stably optimize the objective function with improved generalization. We further develop efficient approximations that make POET flexible and scalable for training large-scale neural networks. Extensive experiments validate the effectiveness and scalability of POET in training LLMs.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.