Lazy Lagrangians with Predictions for Online Learning
Anderson, Daron, Iosifidis, George, Leith, Douglas J.
We consider the general problem of online convex optimization with time-varying additive constraints in the presence of predictions for the next cost and constraint functions. A novel primal-dual algorithm is designed by combining a Follow-The-Regularized-Leader iteration with prediction-adaptive dynamic steps. The algorithm achieves $\mathcal O(T^{\frac{3-\beta}{4}})$ regret and $\mathcal O(T^{\frac{1+\beta}{2}})$ constraint violation bounds that are tunable via parameter $\beta\!\in\![1/2,1)$ and have constant factors that shrink with the predictions quality, achieving eventually $\mathcal O(1)$ regret for perfect predictions. Our work extends the FTRL framework for this constrained OCO setting and outperforms the respective state-of-the-art greedy-based solutions, without imposing conditions on the quality of predictions, the cost functions or the geometry of constraints, beyond convexity.
Jan-8-2022
- Country:
- Europe
- Ireland > Leinster
- County Dublin > Dublin (0.14)
- Netherlands (0.14)
- Ireland > Leinster
- Europe
- Genre:
- Research Report (0.50)
- Industry:
- Education > Educational Setting > Online (0.41)