Lower Bounds for Adversarially Robust PAC Learning under Evasion and Hybrid Attacks

Author(s):  
Dimitrios I. Diochnos ◽  
Saeed Mahloujifar ◽  
Mohammad Mahmoody
Keyword(s):  
2020 ◽  
Vol 34 (04) ◽  
pp. 5644-5651
Author(s):  
Dhruti Shah ◽  
Tuhinangshu Choudhury ◽  
Nikhil Karamchandani ◽  
Aditya Gopalan

We consider the problem of adaptively PAC-learning a probability distribution 𝒫's mode by querying an oracle for information about a sequence of i.i.d. samples X1, X2, … generated from 𝒫. We consider two different query models: (a) each query is an index i for which the oracle reveals the value of the sample Xi, (b) each query is comprised of two indices i and j for which the oracle reveals if the samples Xi and Xj are the same or not. For these query models, we give sequential mode-estimation algorithms which, at each time t, either make a query to the corresponding oracle based on past observations, or decide to stop and output an estimate for the distribution's mode, required to be correct with a specified confidence. We analyze the query complexity of these algorithms for any underlying distribution 𝒫, and derive corresponding lower bounds on the optimal query complexity under the two querying models.


Author(s):  
Parinya CHALERMSOOK ◽  
Hiroshi IMAI ◽  
Vorapong SUPPAKITPAISARN

2020 ◽  
Vol 148 (2) ◽  
pp. 321-327
Author(s):  
Rodolfo Gutiérrez-Romo ◽  
Carlos Matheus
Keyword(s):  

10.37236/1188 ◽  
1994 ◽  
Vol 1 (1) ◽  
Author(s):  
Geoffrey Exoo

For $k \geq 5$, we establish new lower bounds on the Schur numbers $S(k)$ and on the k-color Ramsey numbers of $K_3$.


Sign in / Sign up

Export Citation Format

Share Document