Lazy Lagrangians with Predictions for Online Learning

Anderson, Daron; Iosifidis, George; Leith, Douglas J.

doi:10.48550/arxiv.2201.02890

Cited by 5 publications

(10 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Namely, Theorem 1 proves that, when utility perturbations are only subject to four mild technical conditions, such as in standard OCO, it is impossible to achieve vanishing fairness-regret. Similar negative results were obtained under different setups of primal-dual learning and online saddle point learning [5,50,62], but they have been devised for specific problem structures (e.g., online matrix games) and thus do not apply to our setting.…”

Section: Contributionssupporting

confidence: 69%

“…In particular, we consider 𝛿 𝛿 𝛿 𝑡 (𝑥 𝑥 𝑥) ≜ 1 𝑇 𝑠 ∈ T 𝑢 𝑢 𝑢 𝑠 (𝑥 𝑥 𝑥) − 𝑢 𝑢 𝑢 𝑡 (𝑥 𝑥 𝑥) to quantify how much the adversary perturbs the average utility by selecting a utility function 𝑢 𝑢 𝑢 𝑡 at timeslot 𝑡 ∈ T . Recall that 𝑥 𝑥 𝑥 ★ ∈ X denotes the optimal allocation under HF objective (5). We denote by Ξ(T ) the set of all possible decompositions of T into sets of contiguous timeslots, i.e., for every {T 1 , T 2 , .…”

Section: Adversarial Model and Impossibility Resultsmentioning

confidence: 99%

“…where 𝑥 𝑥 𝑥 ★ is obtained through either SF (4) or HF (5). We provide the following example to further motivate our choice of horizon-fairness as a performance objective.…”

Section: Hfmentioning

confidence: 99%

See 2 more Smart Citations

Enabling Long-term Fairness in Dynamic Resource Allocation

Si-Salem

Iosifidis

Neglia

2022

Proc. ACM Meas. Anal. Comput. Syst.

View full text Add to dashboard Cite

We study the fairness of dynamic resource allocation problem under the α-fairness criterion. We recognize two different fairness objectives that naturally arise in this problem: the well-understood slot-fairness objective that aims to ensure fairness at every timeslot, and the less explored horizon-fairness objective that aims to ensure fairness across utilities accumulated over a time horizon. We argue that horizon-fairness comes at a lower price in terms of social welfare. We study horizon-fairness with the regret as a performance metric and show that vanishing regret cannot be achieved in presence of an unrestricted adversary. We propose restrictions on the adversary's capabilities corresponding to realistic scenarios and an online policy that indeed guarantees vanishing regret under these restrictions. We demonstrate the applicability of the proposed fairness framework to a representative resource management problem considering a virtualized caching system where different caches cooperate to serve content requests.

show abstract

Section: Contributionssupporting

confidence: 69%

Section: Adversarial Model and Impossibility Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Enabling Long-term Fairness in Dynamic Resource Allocation

Si-Salem

Iosifidis

Neglia

2022

Proc. ACM Meas. Anal. Comput. Syst.

View full text Add to dashboard Cite

show abstract

“…4.1 proves that, when utility perturbations are only subject to four mild technical conditions, such as in standard OCO, it is impossible to achieve vanishing fairness-regret. Similar negative results were obtained under different setups of primal-dual learning and online saddle point learning [257][258][259], but they have been devised for specific problem structures (e.g., online matrix games) and thus do not apply to our setting.…”

Section: Contributionssupporting

confidence: 68%

Online Learning for Network Resource Allocation

Salem

2022

SIGMETRICS Perform. Eval. Rev.

View full text Add to dashboard Cite

show abstract

“…) regret bounds. Specifically, OFTRL versions have been proposed in [24] and recently used in [55] for problems with budget constraints, while [15], [17] tailored these ideas to continuous caching. The problem of discrete caching is fundamentally different.…”

Section: Optimistic Learningmentioning

confidence: 99%

Optimistic No-regret Algorithms for Discrete Caching

Mhaisen¹,

Sinha²,

Paschos³

et al. 2022

Preprint

View full text Add to dashboard Cite

We take a systematic look at the problem of storing whole files in a cache with limited capacity in the context of optimistic learning, where the caching policy has access to a prediction oracle (provided by, e.g., a Neural Network). The successive file requests are assumed to be generated by an adversary, and no assumption is made on the accuracy of the oracle. In this setting, we provide a universal lower bound for prediction-assisted online caching and proceed to design a suite of policies with a range of performance-complexity trade-offs. All proposed policies offer sublinear regret bounds commensurate with the accuracy of the oracle. Our results substantially improve upon all recently-proposed online caching policies, which, being unable to exploit the oracle predictions, offer only O( √ T ) regret. In this pursuit, we design, to the best of our knowledge, the first comprehensive optimistic Follow-the-Perturbed leader policy, which generalizes beyond the caching problem. We also study the problem of caching files with different sizes and the bipartite network caching problem. Finally, we evaluate the efficacy of the proposed policies through extensive numerical experiments using real-world traces. I. INTRODUCTIONThis paper addresses the discrete caching (prefetching) problem: choose files to replicate in a local cache in order to maximize the probability that a new file request is served locally. Hitting the cache speeds up CPU, optimizes user experience in CDN's [1], and enhances the performance of wireless networks [2]. With the perpetual growth of Internet traffic fueled by new services such as AR/VR [3], caching policies that learn fast to maximize cache hits can mitigate the increasing costs of information transportation [4], and similar benefits can be expected for embedded and

show abstract

Lazy Lagrangians with Predictions for Online Learning

Cited by 5 publications

References 0 publications

Enabling Long-term Fairness in Dynamic Resource Allocation

Enabling Long-term Fairness in Dynamic Resource Allocation

Online Learning for Network Resource Allocation

Optimistic No-regret Algorithms for Discrete Caching

Contact Info

Product

Resources

About