Proceedings of the forty-sixth annual ACM symposium on Theory of computing最新文献_第8页

Homological product codes 同源产品编码

Proceedings of the forty-sixth annual ACM symposium on Theory of computing Pub Date : 2013-11-04 DOI: 10.1145/2591796.2591870

S. Bravyi, M. Hastings

引用次数: 85

Bandits with switching costs: T2/3 regret 有转换成本的强盗:T2/3后悔

Proceedings of the forty-sixth annual ACM symposium on Theory of computing Pub Date : 2013-10-10 DOI: 10.1145/2591796.2591868

O. Dekel, Jian Ding, Tomer Koren, Y. Peres

{"title":"Bandits with switching costs: T2/3 regret","authors":"O. Dekel, Jian Ding, Tomer Koren, Y. Peres","doi":"10.1145/2591796.2591868","DOIUrl":"https://doi.org/10.1145/2591796.2591868","url":null,"abstract":"We study the adversarial multi-armed bandit problem in a setting where the player incurs a unit cost each time he switches actions. We prove that the player's T-round minimax regret in this setting is [EQUATION], thereby closing a fundamental gap in our understanding of learning with bandit feedback. In the corresponding full-information version of the problem, the minimax regret is known to grow at a much slower rate of Θ(√T). The difference between these two rates provides the first indication that learning with bandit feedback can be significantly harder than learning with full information feedback (previous results only showed a different dependence on the number of actions, but not on T.) In addition to characterizing the inherent difficulty of the multi-armed bandit problem with switching costs, our results also resolve several other open problems in online learning. One direct implication is that learning with bandit feedback against bounded-memory adaptive adversaries has a minimax regret of [EQUATION]. Another implication is that the minimax regret of online learning in adversarial Markov decision processes (MDPs) is [EQUATION]. The key to all of our results is a new randomized construction of a multi-scale random walk, which is of independent interest and likely to prove useful in additional settings.","PeriodicalId":123501,"journal":{"name":"Proceedings of the forty-sixth annual ACM symposium on Theory of computing","volume":"47 43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123996715","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 84

The asymptotic k-SAT threshold 渐近k-SAT阈值

Proceedings of the forty-sixth annual ACM symposium on Theory of computing Pub Date : 2013-10-10 DOI: 10.1145/2591796.2591822

A. Coja-Oghlan

{"title":"The asymptotic k-SAT threshold","authors":"A. Coja-Oghlan","doi":"10.1145/2591796.2591822","DOIUrl":"https://doi.org/10.1145/2591796.2591822","url":null,"abstract":"Since the early 2000s physicists have developed an ingenious but non-rigorous formalism called the cavity method to put forward precise conjectures as to the phase transitions in random constraint satisfaction problems (\"CSPs\"). The cavity method comes in two versions: the simpler replica symmetric variant, and the more intricate 1-step replica symmetry breaking (\"1RSB\") version. While typically the former only gives upper and lower bounds, the latter is conjectured to yield precise results in many cases. By now, there are a number of examples where the replica symmetric bounds have been verified rigorously. However, verifications of 1RSB predictions are scarce. Perhaps the most prominent challenge in this context is that of pinning down the random k-SAT threshold rk--SAT. Here we prove that rk--SAT = 2k ln 2--1/2 (1 + ln 2) + ok(1), which matches the 1RSB prediction up to the ok(1) error term. The proof directly employs ideas from the 1RSB cavity method, such as the notion of covers (relaxed satisfying assignments) and bits of the Survey Propagation calculations. The best previous lower bound was rk--SAT ≥ 2k ln 2--3/2 ln 2 + ok(1), matching the replica symmetric lower bound asymptotically [Coja-Oghlan, Panagiotou: STOC 2013].","PeriodicalId":123501,"journal":{"name":"Proceedings of the forty-sixth annual ACM symposium on Theory of computing","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126601615","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 102

Every list-decodable code for high noise has abundant near-optimal rate puncturings 对于高噪声，每个列表可解码的代码都有大量的接近最佳速率的穿孔

Proceedings of the forty-sixth annual ACM symposium on Theory of computing Pub Date : 2013-10-07 DOI: 10.1145/2591796.2591797

A. Rudra, Mary Wootters

引用次数: 51

Multiway cut, pairwise realizable distributions, and descending thresholds 多路切割，成对可实现的分布和下降阈值

Proceedings of the forty-sixth annual ACM symposium on Theory of computing Pub Date : 2013-09-10 DOI: 10.1145/2591796.2591866

Ankit Sharma, J. Vondrák

引用次数: 50

Testing surface area with arbitrary accuracy 以任意精度测试表面积

Proceedings of the forty-sixth annual ACM symposium on Theory of computing Pub Date : 2013-09-05 DOI: 10.1145/2591796.2591807

Joe Neeman

引用次数: 22

A strongly polynomial algorithm for generalized flow maximization 广义流量最大化的强多项式算法

Proceedings of the forty-sixth annual ACM symposium on Theory of computing Pub Date : 2013-07-25 DOI: 10.1145/2591796.2591806

László A. Végh

引用次数: 37

Query complexity of approximate nash equilibria 近似纳什均衡的查询复杂度

Proceedings of the forty-sixth annual ACM symposium on Theory of computing Pub Date : 2013-06-27 DOI: 10.1145/2591796.2591829

Y. Babichenko

引用次数: 54

Fourier PCA and robust tensor decomposition 傅里叶主成分分析和鲁棒张量分解

Proceedings of the forty-sixth annual ACM symposium on Theory of computing Pub Date : 2013-06-24 DOI: 10.1145/2591796.2591875

Navin Goyal, S. Vempala, Ying Xiao

引用次数: 89

Communication is bounded by root of rank 交流受等级的限制

Proceedings of the forty-sixth annual ACM symposium on Theory of computing Pub Date : 2013-06-07 DOI: 10.1145/2591796.2591799

Shachar Lovett

引用次数: 60