arXiv subjects

G. Neglia

Publications and source records attributed to G. Neglia.

5 recordsLinked to original sources

arXiv2023

Towards Inference Delivery Networks: Distributing Machine Learning with Optimality Guarantees

An increasing number of applications rely on complex inference tasks that are based on machine learning (ML). Currently, there are two options to run such tasks: either they are served directly by the end device (e.g., smartphones, IoT equipment, smart vehicles), or offloaded to a remote cloud. Both options may be unsatisfactory for many applications: local models may have inadequate accuracy, while the cloud may fail to meet delay constraints. In this paper, we present the novel idea of inference delivery networks (IDNs), networks of computing nodes that coordinate to satisfy ML inference requests achieving the best trade-off between latency and accuracy. IDNs bridge the dichotomy between device and cloud execution by integrating inference delivery at the various tiers of the infrastructure continuum (access, edge, regional data center, cloud). We propose a distributed dynamic policy for ML model allocation in an IDN by which each node dynamically updates its local set of inference models based on requests observed during the recent past plus limited information exchange with its neighboring nodes. Our policy offers strong performance guarantees in an adversarial setting and shows improvements over greedy heuristics with similar complexity in realistic scenarios.

cs.NI↗

arXiv2023

No-Regret Caching via Online Mirror Descent

We study an online caching problem in which requests can be served by a local cache to avoid retrieval costs from a remote server. The cache can update its state after a batch of requests and store an arbitrarily small fraction of each file. We study no-regret algorithms based on Online Mirror Descent (OMD) strategies. We show that bounds for the regret crucially depend on the diversity of the request process, provided by the diversity ratio R/h, where R is the size of the batch, and h is the maximum multiplicity of a request in a given batch. We characterize the optimality of OMD caching policies w.r.t. regret under different diversity regimes. We also prove that, when the cache must store the entire file, rather than a fraction, OMD strategies can be coupled with a randomized rounding scheme that preserves regret guarantees, even when update costs cannot be neglected. We provide a formal characterization of the rounding problem through optimal transport theory, and moreover we propose a computationally efficient randomized rounding scheme.

cs.LG↗

arXiv2022

Enabling Long-term Fairness in Dynamic Resource Allocation

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.

cs.GT↗

arXiv2022

Ascent Similarity Caching with Approximate Indexes

Similarity search is a key operation in multimedia retrieval systems and recommender systems, and it will play an important role also for future machine learning and augmented reality applications. When these systems need to serve large objects with tight delay constraints, edge servers close to the end-user can operate as similarity caches to speed up the retrieval. In this paper we present AÇAI, a new similarity caching policy which improves on the state of the art by using (i) an (approximate) index for the whole catalog to decide which objects to serve locally and which to retrieve from the remote server, and (ii) a mirror ascent algorithm to update the set of local objects with strong guarantees even when the request process does not exhibit any statistical regularity.

cs.NI↗

arXiv2010

MAC design for WiFi infrastructure networks: a game-theoretic approach

In WiFi networks, mobile nodes compete for accessing a shared channel by means of a random access protocol called Distributed Coordination Function (DCF). Although this protocol is in principle fair, since all the stations have the same probability to transmit on the channel, it has been shown that unfair behaviors may emerge in actual networking scenarios because of non-standard configurations of the nodes. Due to the proliferation of open source drivers and programmable cards, enabling an easy customization of the channel access policies, we propose a game-theoretic analysis of random access schemes. Assuming that each node is rational and implements a best response strategy, we show that efficient equilibria conditions can be reached when stations are interested in both uploading and downloading traffic. More interesting, these equilibria are reached when all the stations play the same strategy, thus guaranteeing a fair resource sharing. When stations are interested in upload traffic only, we also propose a mechanism design, based on an artificial dropping of layer-2 acknowledgments, to force desired equilibria. Finally, we propose and evaluate some simple DCF extensions for practically implementing our theoretical findings.

cs.GT↗