REVIEW 10 cited by
Introduction to Online Convex Optimization
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
Signed reviews
read the original abstract
This manuscript portrays optimization as a process. In many practical applications the environment is so complex that it is infeasible to lay out a comprehensive theoretical model and use classical algorithmic theory and mathematical optimization. It is necessary as well as beneficial to take a robust approach, by applying an optimization method that learns as one goes along, learning from experience as more aspects of the problem are observed. This view of optimization as a process has become prominent in varied fields and has led to some spectacular success in modeling and systems that are now part of our daily lives.
Forward citations
Cited by 10 Pith papers
-
A Linearly Convergent Projection-Free Algorithm for Smooth Convex Sets
This paper presents a projection-free algorithm that converges linearly for strongly convex minimization over convex sets satisfying a uniform rolling-ball condition, using only membership queries.
-
Instance-Optimal Matrix Multiplicative Weight Update and Its Quantum Applications
A new potential-based algorithm achieves instance-optimal O(sqrt(T·S(X||I/d))) regret for matrix LEA with the same complexity as MMWU, using a one-sided Jensen trace inequality.
-
Blackwell's Approachability with Approximation Algorithms
Blackwell approachability with approximation oracles for both players: the downward closure of α_X α_Y^{-1} S is efficiently approachable at rate O(1/sqrt(T)).
-
Decoupling Corruption and Horizon in Robust Contextual Pricing
Robust contextual pricing admits regret O(Cd + d² log T), the first bound that additively separates corruption budget C from horizon T.
-
Online Learning and Unlearning
Two OGD-based algorithms provably make deleted points statistically invisible in future outputs while adding only modest regret overhead.
-
Lower Bound on the Cumulative Constrained Violation for the OGD+Projection algorithm for Constrained Online Convex Optimization (COCO)
OGD+Projection for constrained online convex optimization has cumulative constraint violation Ω(T^{(d-1)/(2d)}) in dimension d, the first lower bound of this form.
-
Scheduzz: Constraint-based Fuzz Driver Generation with Dual Scheduling
Scheduzz combines LLM-extracted API usage constraints with a dual scheduling loop to automatically generate and run fuzz drivers, beating existing tools in coverage and finding 33 bugs in real libraries.
-
Rethinking Pricing in Energy Markets: Pay-as-Bid vs Pay-as-Clear
A game-theoretic comparison shows pay-as-bid's worst-case equilibrium price is at most pay-as-clear's, with strict gains in generic instances.
-
An Optimistic Algorithm for Online Convex Optimization with Adversarial Constraints
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.
- Optimal Online Bookmaking for Binary Games
Discussion (0). Continue with ORCID to comment.