equal task sampling

**Equal task sampling** is **sampling each task with equal probability regardless of dataset size** - This strategy protects low-resource tasks from being overshadowed by high-volume datasets. **What Is Equal task sampling?** - **Definition**: Sampling each task with equal probability regardless of dataset size. - **Core Mechanism**: This strategy protects low-resource tasks from being overshadowed by high-volume datasets. - **Operational Scope**: It is applied during data scheduling, parameter updates, or architecture design to preserve capability stability across many objectives. - **Failure Modes**: Large tasks may become underutilized, reducing overall data efficiency. **Why Equal task sampling Matters** - **Retention and Stability**: It helps maintain previously learned behavior while new tasks are introduced. - **Transfer Efficiency**: Strong design can amplify positive transfer and reduce duplicate learning across tasks. - **Compute Use**: Better task orchestration improves return from fixed training budgets. - **Risk Control**: Explicit monitoring reduces silent regressions in legacy capabilities. - **Program Governance**: Structured methods provide auditable rules for updates and rollout decisions. **How It Is Used in Practice** - **Design Choice**: Select the method based on task relatedness, retention requirements, and latency constraints. - **Calibration**: Use equal sampling as a baseline and compare against adaptive methods on both macro and per-task metrics. - **Validation**: Track per-task gains, retention deltas, and interference metrics at every major checkpoint. Equal task sampling is **a core method in continual and multi-task model optimization** - It promotes fairness across tasks and stabilizes coverage in heterogeneous portfolios.