No-Regret Caching with Noisy Request Estimates

• URL: http://arxiv.org/abs/2309.02055v1
• Date: Tue, 5 Sep 2023 08:57:35 GMT
• Title: No-Regret Caching with Noisy Request Estimates
• Authors: Younes Ben Mazziane, Francescomaria Faticanti, Giovanni Neglia, Sara Alouf
• Abstract summary: We propose the Noisy-Follow-the-Perturbed-Leader (NFPL) algorithm, a variant of the classic Follow-the-Perturbed-Leader (FPL) when request estimates are noisy. We show that the proposed solution has sublinear regret under specific conditions on the requests estimator.
• Score: 12.603423174002254
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Online learning algorithms have been successfully used to design caching policies with regret guarantees. Existing algorithms assume that the cache knows the exact request sequence, but this may not be feasible in high load and/or memory-constrained scenarios, where the cache may have access only to sampled requests or to approximate requests' counters. In this paper, we propose the Noisy-Follow-the-Perturbed-Leader (NFPL) algorithm, a variant of the classic Follow-the-Perturbed-Leader (FPL) when request estimates are noisy, and we show that the proposed solution has sublinear regret under specific conditions on the requests estimator. The experimental evaluation compares the proposed solution against classic caching policies and validates the proposed approach under both synthetic and real request traces.

Related papers

• On the Regret of Coded Caching with Adversarial Requests [7.171698704686835]
  We study the well-known coded caching problem in an online learning framework, wherein requests arrive sequentially. We introduce a caching policy based on the Follow-The-Perturbed-Leader principle and show that for any time horizon T, it achieves a sub-linear regret of mathcalO(sqrt(T).
  arXiv  Detail & Related papers  (2024-09-19T01:13:03Z)
• An Online Gradient-Based Caching Policy with Logarithmic Complexity and Regret Guarantees [13.844896723580858]
  We introduce a new variant of the gradient-based online caching policy that achieves groundbreaking logarithmic computational complexity. This advancement allows us to test the policy on large-scale, real-world traces featuring millions of requests and items.
  arXiv  Detail & Related papers  (2024-05-02T13:11:53Z)
• Mitigating LLM Hallucinations via Conformal Abstention [70.83870602967625]
  We develop a principled procedure for determining when a large language model should abstain from responding in a general domain. We leverage conformal prediction techniques to develop an abstention procedure that benefits from rigorous theoretical guarantees on the hallucination rate (error rate) Experimentally, our resulting conformal abstention method reliably bounds the hallucination rate on various closed-book, open-domain generative question answering datasets.
  arXiv  Detail & Related papers  (2024-04-04T11:32:03Z)
• Likelihood Ratio Confidence Sets for Sequential Decision Making [51.66638486226482]
  We revisit the likelihood-based inference principle and propose to use likelihood ratios to construct valid confidence sequences. Our method is especially suitable for problems with well-specified likelihoods. We show how to provably choose the best sequence of estimators and shed light on connections to online convex optimization.
  arXiv  Detail & Related papers  (2023-11-08T00:10:21Z)
• Optimistic No-regret Algorithms for Discrete Caching [6.182368229968862]
  We take a systematic look at the problem of storing whole files in a cache with limited capacity in the context of optimistic learning. We provide a universal lower bound for prediction-assisted online caching and design a suite of policies with a range of performance-complexity trade-offs. Our results substantially improve upon all recently-proposed online caching policies, which, being unable to exploit the oracle predictions, offer only $O(sqrtT)$ regret.
  arXiv  Detail & Related papers  (2022-08-15T09:18:41Z)
• Intelligent Request Strategy Design in Recommender System [76.90734681369156]
  We envision a new learning task of edge intelligence named Intelligent Request Strategy Design (IRSD) IRSD aims to improve the effectiveness of waterfall RSs by determining the appropriate occasions of request insertion based on users' real-time intention. We propose a new paradigm of adaptive request insertion strategy named Uplift-based On-edge Smart Request Framework (AdaRequest)
  arXiv  Detail & Related papers  (2022-06-23T16:51:38Z)
• Online Caching with no Regret: Optimistic Learning via Recommendations [15.877673959068458]
  We build upon the Follow-the-Regularized-Leader (FTRL) framework to include predictions for the file requests. We extend the framework to learn and utilize the best request predictor in cases where many are available. We prove that the proposed optimistic learning caching policies can achieve sub-zero performance loss (regret) for perfect predictions.
  arXiv  Detail & Related papers  (2022-04-20T09:29:47Z)
• Accelerating Deep Learning Classification with Error-controlled Approximate-key Caching [72.50506500576746]
  We propose a novel caching paradigm, that we named approximate-key caching. While approximate cache hits alleviate DL inference workload and increase the system throughput, they however introduce an approximation error. We analytically model our caching system performance for classic LRU and ideal caches, we perform a trace-driven evaluation of the expected performance, and we compare the benefits of our proposed approach with the state-of-the-art similarity caching.
  arXiv  Detail & Related papers  (2021-12-13T13:49:11Z)
• Local policy search with Bayesian optimization [73.0364959221845]
  Reinforcement learning aims to find an optimal policy by interaction with an environment. Policy gradients for local search are often obtained from random perturbations. We develop an algorithm utilizing a probabilistic model of the objective function and its gradient.
  arXiv  Detail & Related papers  (2021-06-22T16:07:02Z)
• Variance-Reduced Off-Policy Memory-Efficient Policy Search [61.23789485979057]
  Off-policy policy optimization is a challenging problem in reinforcement learning. Off-policy algorithms are memory-efficient and capable of learning from off-policy samples.
  arXiv  Detail & Related papers  (2020-09-14T16:22:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.