Pith. sign in

REVIEW 4 cited by

Projection-free 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 1206.4657 v1 pith:PLNVEA7M submitted 2012-06-18 cs.LG cs.DS

classification cs.LGcs.DS
keywords onlinealgorithmslearningoptimizationboundscomputationalconvexefficient
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

The computational bottleneck in applying online learning to massive data sets is usually the projection step. We present efficient online learning algorithms that eschew projections in favor of much more efficient linear optimization steps using the Frank-Wolfe technique. We obtain a range of regret bounds for online convex optimization, with better bounds for specific cases such as stochastic online smooth convex optimization. Besides the computational advantage, other desirable features of our algorithms are that they are parameter-free in the stochastic case and produce sparse decisions. We apply our algorithms to computationally intensive applications of collaborative filtering, and show the theoretical improvements to be clearly visible on standard datasets.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

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

  1. Oracle-Based Distributionally Robust Optimization under Optimal Transport Ambiguity Sets

    math.OC 2026-08 conditional novelty 7.0 of 10

    The paper reduces worst-case expectation in transport-based DRO to a scalar budget allocation and gives a scalable oracle-based algorithm plus a tight new support bound for the dual problem.

  2. Training Deep Learning Models with Norm-Constrained LMOs

    cs.LG 2025-02 unverdicted novelty 7.0 of 10

    Scion is a new stochastic LMO-based optimizer family that unifies existing methods, supports unconstrained problems, and delivers hyperparameter transferability plus speedups on nanoGPT training.

  3. Quantum Algorithms for Projection-Free Sparse Convex Optimization

    quant-ph 2025-07 conditional novelty 5.0 of 10

    Quantum Frank-Wolfe algorithms reduce dimension dependence in sparse convex optimization, from O(d) to O(sqrt d) function queries for vectors and from O(d^2) to O(d) per update step for matrices under certain assumptions.

  4. Strongly Convex Maximization via the Frank-Wolfe Algorithm with the Kurdyka-{\L}ojasiewicz Inequality

    math.OC 2025-04 conditional novelty 5.0 of 10

    Under smoothness, strong convexity, and the Kurdyka-Lojasiewicz property, the greedy Frank-Wolfe sequence converges to a critical point, with rates that depend on the KL exponent.

Pith tools