- claim-1-tpgd-algorithm-1-is-a-two-phase-first-order-gradient-descent-method
- claim-2-phase-i-performs-k1-2-iterations-of-unregularized-gradient-descent
- claim-3-theorem-5-1-and-corollary-5-3-prove-the-method-attains
- claim-4-the-algorithm-achieves-1-iteration-complexity-i-e-convergence-in
- claim-5-the-estimation-error-guarantee-requires-a-per-task-sample-size-of
- claim-6-theorem-5-4-establishes-excess-risk-bounds-for-transferring-the-learned
- conclusion
- executive-summary
- 1.18 kB