DiBS‑MTL stays robust to arbitrary loss rescaling and converges to Pareto‑stationary points even with nonconvex losses. The paper was submitted in September 2025. Read more: https://getnews.me/dibs-mtl-introduces-transformation-invariant-multitask-learning/ #multitasklearning #dibsmtl
September 30, 2025 at 4:13 PM
DiBS‑MTL stays robust to arbitrary loss rescaling and converges to Pareto‑stationary points even with nonconvex losses. The paper was submitted in September 2025. Read more: https://getnews.me/dibs-mtl-introduces-transformation-invariant-multitask-learning/ #multitasklearning #dibsmtl