PPE is a novel predictor-corrector method for interactive Pareto set exploration in deep multi-task learning that approximates tangent spaces via Krylov subspace iterations using only matrix-vector products from automatic differentiation.
National Sci- ence Review5(1), 30–43 (09 2017)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Interactive Pareto navigation for deep multi-task learning
PPE is a novel predictor-corrector method for interactive Pareto set exploration in deep multi-task learning that approximates tangent spaces via Krylov subspace iterations using only matrix-vector products from automatic differentiation.