@article{memoryaugmentedtransformerscanimplement, title = {Toward generalizable learning of all (linear) first-order methods via memory augmented Transformers}, author = {Sanchayan Dutta and Suvrit Sra}, year = {2024}, eprint = {2410.07263}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.07263v3}, }