Competitive strategies to use "warm start" algorithms with predictions

• URL: http://arxiv.org/abs/2405.03661v1
• Date: Mon, 6 May 2024 17:38:20 GMT
• Title: Competitive strategies to use "warm start" algorithms with predictions
• Authors: Vaidehi Srinivas, Avrim Blum,
• Abstract summary: We consider the problem of learning and using predictions for warm start algorithms with predictions. In this setting, an algorithm is given an instance of a problem, and a prediction of the solution. We give competitive guarantees against stronger benchmarks that consider a set of $k$ predictions.
• Score: 12.970501425097645
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We consider the problem of learning and using predictions for warm start algorithms with predictions. In this setting, an algorithm is given an instance of a problem, and a prediction of the solution. The runtime of the algorithm is bounded by the distance from the predicted solution to the true solution of the instance. Previous work has shown that when instances are drawn iid from some distribution, it is possible to learn an approximately optimal fixed prediction (Dinitz et al, NeurIPS 2021), and in the adversarial online case, it is possible to compete with the best fixed prediction in hindsight (Khodak et al, NeurIPS 2022). In this work we give competitive guarantees against stronger benchmarks that consider a set of $k$ predictions $\mathbf{P}$. That is, the "optimal offline cost" to solve an instance with respect to $\mathbf{P}$ is the distance from the true solution to the closest member of $\mathbf{P}$. This is analogous to the $k$-medians objective function. In the distributional setting, we show a simple strategy that incurs cost that is at most an $O(k)$ factor worse than the optimal offline cost. We then show a way to leverage learnable coarse information, in the form of partitions of the instance space into groups of "similar" instances, that allows us to potentially avoid this $O(k)$ factor. Finally, we consider an online version of the problem, where we compete against offline strategies that are allowed to maintain a moving set of $k$ predictions or "trajectories," and are charged for how much the predictions move. We give an algorithm that does at most $O(k^4 \ln^2 k)$ times as much work as any offline strategy of $k$ trajectories. This algorithm is deterministic (robust to an adaptive adversary), and oblivious to the setting of $k$. Thus the guarantee holds for all $k$ simultaneously.

Related papers

• Fair Secretaries with Unfair Predictions [12.756552522270198]
  We show that an algorithm can have zero probability of accepting the best candidate, which we deem unfair, despite promising to accept a candidate whose expected value is at least $maxOmega (1), 1 - O(epsilon)$ times the optimal value, where $epsilon$ is the prediction error. Our algorithm and analysis are based on a new "pegging" idea that diverges from existing works and simplifies/unifies some of their results.
  arXiv  Detail & Related papers  (2024-11-15T00:23:59Z)
• Mixing predictions for online metric algorithms [34.849039387367455]
  We design algorithms that combine predictions and are competitive against such dynamic combinations. Our algorithms can be adapted to access predictors in a bandit-like fashion, querying only one predictor at a time. An unexpected implication of one of our lower bounds is a new structural insight about covering formulations for the $k$-server problem.
  arXiv  Detail & Related papers  (2023-04-04T13:18:00Z)
• Streaming Algorithms for Learning with Experts: Deterministic Versus Robust [62.98860182111096]
  In the online learning with experts problem, an algorithm must make a prediction about an outcome on each of $T$ days (or times) The goal is to make a prediction with the minimum cost, specifically compared to the best expert in the set. We show a space lower bound of $widetildeOmegaleft(fracnMRTright)$ for any deterministic algorithm that achieves regret $R$ when the best expert makes $M$ mistakes.
  arXiv  Detail & Related papers  (2023-03-03T04:39:53Z)
• Estimating Optimal Policy Value in General Linear Contextual Bandits [50.008542459050155]
  In many bandit problems, the maximal reward achievable by a policy is often unknown in advance. We consider the problem of estimating the optimal policy value in the sublinear data regime before the optimal policy is even learnable. We present a more practical, computationally efficient algorithm that estimates a problem-dependent upper bound on $V*$.
  arXiv  Detail & Related papers  (2023-02-19T01:09:24Z)
• Mind the gap: Achieving a super-Grover quantum speedup by jumping to the end [114.3957763744719]
  We present a quantum algorithm that has rigorous runtime guarantees for several families of binary optimization problems. We show that the algorithm finds the optimal solution in time $O*(2(0.5-c)n)$ for an $n$-independent constant $c$. We also show that for a large fraction of random instances from the $k$-spin model and for any fully satisfiable or slightly frustrated $k$-CSP formula, statement (a) is the case.
  arXiv  Detail & Related papers  (2022-12-03T02:45:23Z)
• Scheduling with Speed Predictions [10.217102227210669]
  We study the speed-robust scheduling problem where the speeds of the machines, instead of the processing times of the jobs, are unknown. Our main result is an algorithm that achieves a $mineta2 (1+epsilon)2 (1+epsilon)(2 + 2/alpha)$ approximation. When the predictions are accurate, this approximation improves over the previously best known approximation of $2-1/m$ for speed-robust scheduling.
  arXiv  Detail & Related papers  (2022-05-02T23:39:41Z)
• Online Optimization with Untrusted Predictions [7.895232155155041]
  We study the problem of online optimization, where a decision maker must choose points in a general metric space to the sum of per-round, non-competitive hitting costs and the costs of switching between rounds. We propose a novel algorithm, Adaptive Online Switching (AOS), and prove that, for any desired $delta 0)$competitive if predictions are perfect, it is $tildecalO(alphadelta)$ even when predictions are inaccurate.
  arXiv  Detail & Related papers  (2022-02-07T21:08:02Z)
• Maximizing Determinants under Matroid Constraints [69.25768526213689]
  We study the problem of finding a basis $S$ of $M$ such that $det(sum_i in Sv_i v_i v_itop)$ is maximized. This problem appears in a diverse set of areas such as experimental design, fair allocation of goods, network design, and machine learning.
  arXiv  Detail & Related papers  (2020-04-16T19:16:38Z)
• Taking a hint: How to leverage loss predictors in contextual bandits? [63.546913998407405]
  We study learning in contextual bandits with the help of loss predictors. We show that the optimal regret is $mathcalO(minsqrtT, sqrtmathcalETfrac13)$ when $mathcalE$ is known.
  arXiv  Detail & Related papers  (2020-03-04T07:36:38Z)
• Locally Private Hypothesis Selection [96.06118559817057]
  We output a distribution from $mathcalQ$ whose total variation distance to $p$ is comparable to the best such distribution. We show that the constraint of local differential privacy incurs an exponential increase in cost. Our algorithms result in exponential improvements on the round complexity of previous methods.
  arXiv  Detail & Related papers  (2020-02-21T18:30:48Z)

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.