{"ID":2896563,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.04707","arxiv_id":"2508.04707","title":"From Rattle to Roar: Optimizer Showdown for MambaStock on S\u0026P 500","abstract":"We evaluate the performance of several optimizers on the task of forecasting S\u0026P 500 Index returns with the MambaStock model. Among the most widely used algorithms, gradient-smoothing and adaptive-rate optimizers (for example, Adam and RMSProp) yield the lowest test errors. In contrast, the Lion optimizer offers notably faster training. To combine these advantages, we introduce a novel family of optimizers, Roaree, that dampens the oscillatory loss behavior often seen with Lion while preserving its training speed.","short_abstract":"We evaluate the performance of several optimizers on the task of forecasting S\u0026P 500 Index returns with the MambaStock model. Among the most widely used algorithms, gradient-smoothing and adaptive-rate optimizers (for example, Adam and RMSProp) yield the lowest test errors. In contrast, the Lion optimizer offers notabl...","url_abs":"https://arxiv.org/abs/2508.04707","url_pdf":"https://arxiv.org/pdf/2508.04707v1","authors":"[\"Alena Chan\",\"Maria Garmonina\"]","published":"2025-07-09T12:51:24Z","proceeding":"q-fin.CP","tasks":"[\"q-fin.CP\",\"cs.LG\"]","methods":"[]","has_code":false}