Matches in SemOpenAlex for { <https://semopenalex.org/work/W2925933452> ?p ?o ?g. }
- W2925933452 abstract "Packet classification is a fundamental problem in computer networking. This problem exposes a hard tradeoff between the computation and state complexity, which makes it particularly challenging. To navigate this tradeoff, existing solutions rely on complex hand-tuned heuristics, which are brittle and hard to optimize. In this paper, we propose a deep reinforcement learning (RL) approach to solve the packet classification problem. There are several characteristics that make this problem a good fit for Deep RL. First, many of the existing solutions are iteratively building a decision tree by splitting nodes in the tree. Second, the effects of these actions (e.g., splitting nodes) can only be evaluated once we are done with building the tree. These two characteristics are naturally captured by the ability of RL to take actions that have sparse and delayed rewards. Third, it is computationally efficient to generate data traces and evaluate decision trees, which alleviate the notoriously high sample complexity problem of Deep RL algorithms. Our solution, NeuroCuts, uses succinct representations to encode state and action space, and efficiently explore candidate decision trees to optimize for a global objective. It produces compact decision trees optimized for a specific set of rules and a given performance metric, such as classification time, memory footprint, or a combination of the two. Evaluation on ClassBench shows that NeuroCuts outperforms existing hand-crafted algorithms in classification time by 18% at the median, and reduces both time and memory footprint by up to 3x." @default.
- W2925933452 created "2019-04-11" @default.
- W2925933452 creator A5012968725 @default.
- W2925933452 creator A5020609129 @default.
- W2925933452 creator A5041920173 @default.
- W2925933452 creator A5064891668 @default.
- W2925933452 date "2019-02-26" @default.
- W2925933452 modified "2023-10-16" @default.
- W2925933452 title "Neural Packet Classification" @default.
- W2925933452 cites W1482647296 @default.
- W2925933452 cites W1757796397 @default.
- W2925933452 cites W1999156278 @default.
- W2925933452 cites W2020145470 @default.
- W2925933452 cites W2022106793 @default.
- W2925933452 cites W2050600889 @default.
- W2925933452 cites W2119706632 @default.
- W2925933452 cites W2119850747 @default.
- W2925933452 cites W2120416631 @default.
- W2925933452 cites W2132347196 @default.
- W2925933452 cites W2137145600 @default.
- W2925933452 cites W2139587756 @default.
- W2925933452 cites W2143377393 @default.
- W2925933452 cites W2143612262 @default.
- W2925933452 cites W2145339207 @default.
- W2925933452 cites W2146398330 @default.
- W2925933452 cites W2150702922 @default.
- W2925933452 cites W2153399290 @default.
- W2925933452 cites W2155771881 @default.
- W2925933452 cites W2155968351 @default.
- W2925933452 cites W2156737235 @default.
- W2925933452 cites W2157054323 @default.
- W2925933452 cites W2157085439 @default.
- W2925933452 cites W2164905748 @default.
- W2925933452 cites W2169383296 @default.
- W2925933452 cites W2220384803 @default.
- W2925933452 cites W2257979135 @default.
- W2925933452 cites W2283196293 @default.
- W2925933452 cites W2343283570 @default.
- W2925933452 cites W2410983263 @default.
- W2925933452 cites W2546571074 @default.
- W2925933452 cites W2736601468 @default.
- W2925933452 cites W2744628735 @default.
- W2925933452 cites W2754517384 @default.
- W2925933452 cites W2766447205 @default.
- W2925933452 cites W2786036274 @default.
- W2925933452 cites W2787074649 @default.
- W2925933452 cites W2788005034 @default.
- W2925933452 cites W2793089345 @default.
- W2925933452 cites W2804047946 @default.
- W2925933452 cites W2805177834 @default.
- W2925933452 cites W2824027552 @default.
- W2925933452 cites W2883529420 @default.
- W2925933452 cites W2898855235 @default.
- W2925933452 cites W2902907165 @default.
- W2925933452 cites W2905224888 @default.
- W2925933452 cites W2949683077 @default.
- W2925933452 cites W2949888546 @default.
- W2925933452 cites W2962736495 @default.
- W2925933452 cites W2962771342 @default.
- W2925933452 cites W2963094322 @default.
- W2925933452 cites W2964043796 @default.
- W2925933452 cites W2964161785 @default.
- W2925933452 cites W79029001 @default.
- W2925933452 cites W2894818483 @default.
- W2925933452 doi "https://doi.org/10.48550/arxiv.1902.10319" @default.
- W2925933452 hasPublicationYear "2019" @default.
- W2925933452 type Work @default.
- W2925933452 sameAs 2925933452 @default.
- W2925933452 citedByCount "0" @default.
- W2925933452 crossrefType "posted-content" @default.
- W2925933452 hasAuthorship W2925933452A5012968725 @default.
- W2925933452 hasAuthorship W2925933452A5020609129 @default.
- W2925933452 hasAuthorship W2925933452A5041920173 @default.
- W2925933452 hasAuthorship W2925933452A5064891668 @default.
- W2925933452 hasBestOaLocation W29259334521 @default.
- W2925933452 hasConcept C111919701 @default.
- W2925933452 hasConcept C113174947 @default.
- W2925933452 hasConcept C11413529 @default.
- W2925933452 hasConcept C119857082 @default.
- W2925933452 hasConcept C127705205 @default.
- W2925933452 hasConcept C134306372 @default.
- W2925933452 hasConcept C154945302 @default.
- W2925933452 hasConcept C158379750 @default.
- W2925933452 hasConcept C162324750 @default.
- W2925933452 hasConcept C176217482 @default.
- W2925933452 hasConcept C177264268 @default.
- W2925933452 hasConcept C199360897 @default.
- W2925933452 hasConcept C21547014 @default.
- W2925933452 hasConcept C311688 @default.
- W2925933452 hasConcept C31258907 @default.
- W2925933452 hasConcept C33923547 @default.
- W2925933452 hasConcept C41008148 @default.
- W2925933452 hasConcept C74912251 @default.
- W2925933452 hasConcept C84525736 @default.
- W2925933452 hasConcept C97541855 @default.
- W2925933452 hasConceptScore W2925933452C111919701 @default.
- W2925933452 hasConceptScore W2925933452C113174947 @default.
- W2925933452 hasConceptScore W2925933452C11413529 @default.
- W2925933452 hasConceptScore W2925933452C119857082 @default.
- W2925933452 hasConceptScore W2925933452C127705205 @default.