Pith. sign in

REVIEW 1 cited by

Lazy Lagrangians with Predictions for Online Learning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2201.02890 v1 pith:3RSNGUYO submitted 2022-01-08 cs.LG cs.NIstat.ML

classification cs.LGcs.NIstat.ML
keywords predictionsbetamathcalalgorithmconstraintconstraintscostfrac
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. An Optimistic Algorithm for Online Convex Optimization with Adversarial Constraints

    stat.ML 2024-12 conditional novelty 6.0 of 10

    An optimistic meta-algorithm achieves O(sqrt(E_T(f))) regret and O(sqrt(E_T(g+)) log T) constraint violation for online convex optimization with adversarial constraints, where E_T measures cumulative prediction error.

Pith tools