TY - GEN
T1 - Asymptotically-Good RLCCs with (log n)2+o(1) Queries
AU - Cohen, Gil
AU - Yankovitz, Tal
N1 - Publisher Copyright:
© Gil Cohen and Tal Yankovitz.
PY - 2024/7
Y1 - 2024/7
N2 - Recently, Kumar and Mon reached a significant milestone by constructing asymptotically good relaxed locally correctable codes (RLCCs) with poly-logarithmic query complexity. Specifically, they constructed n-bit RLCCs with O(log69 n) queries. Their construction relies on a clever reduction to locally testable codes (LTCs), capitalizing on recent breakthrough works in LTCs. As for lower bounds, Gur and Lachish (SICOMP 2021) proved that any asymptotically-good RLCC must make Ω(e √log n) queries. Hence emerges the intriguing question regarding the identity of the least value 12 ≤ e ≤ 69 for which asymptotically-good RLCCs with query complexity (log n)e+o(1) exist. In this work, we make substantial progress in narrowing the gap by devising asymptotically-good RLCCs with a query complexity of (log n)2+o(1). The key insight driving our work lies in recognizing that the strong guarantee of local testability overshoots the requirements for the Kumar-Mon reduction. In particular, we prove that we can replace the LTCs by “vanilla” expander codes which indeed have the necessary property: local testability in the code’s vicinity.
AB - Recently, Kumar and Mon reached a significant milestone by constructing asymptotically good relaxed locally correctable codes (RLCCs) with poly-logarithmic query complexity. Specifically, they constructed n-bit RLCCs with O(log69 n) queries. Their construction relies on a clever reduction to locally testable codes (LTCs), capitalizing on recent breakthrough works in LTCs. As for lower bounds, Gur and Lachish (SICOMP 2021) proved that any asymptotically-good RLCC must make Ω(e √log n) queries. Hence emerges the intriguing question regarding the identity of the least value 12 ≤ e ≤ 69 for which asymptotically-good RLCCs with query complexity (log n)e+o(1) exist. In this work, we make substantial progress in narrowing the gap by devising asymptotically-good RLCCs with a query complexity of (log n)2+o(1). The key insight driving our work lies in recognizing that the strong guarantee of local testability overshoots the requirements for the Kumar-Mon reduction. In particular, we prove that we can replace the LTCs by “vanilla” expander codes which indeed have the necessary property: local testability in the code’s vicinity.
KW - RLCC
KW - RLDC
KW - Relaxed locally decodable codes
KW - Relxaed locally correctable codes
UR - http://www.scopus.com/inward/record.url?scp=85199348767&partnerID=8YFLogxK
U2 - 10.4230/LIPIcs.CCC.2024.8
DO - 10.4230/LIPIcs.CCC.2024.8
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:85199348767
T3 - Leibniz International Proceedings in Informatics, LIPIcs
BT - 39th Computational Complexity Conference, CCC 2024
A2 - Santhanam, Rahul
PB - Schloss Dagstuhl- Leibniz-Zentrum fur Informatik GmbH, Dagstuhl Publishing
T2 - 39th Computational Complexity Conference, CCC 2024
Y2 - 22 July 2024 through 25 July 2024
ER -