User dohmatob

6 votes

1 answer

92 views

Generate cut $(A,B)$ in edge-colored graph $(V,E_1 \cup E_2)$ such that there are more red than white crossings, i.e $|E_1(A,B)| > |E_2(A,B)|$

asked Sep 9, 2020 at 5:59

4 votes

0 answers

114 views

Strong data-processing inequality: bound $TV(T_{\#}P_0,T_{\#}P_1)$ if $\|T(x)-x\|_\infty \le \varepsilon;\forall x \in \mathbb R^p$

asked Dec 25, 2019 at 14:31

3 votes

2 answers

166 views

Worst-case complexity of computing a certain non-standard dot product + algorithms realizing this complexity

asked Mar 8, 2023 at 23:33

3 votes

1 answer

149 views

Fast private computation of dot product

asked Nov 25, 2020 at 18:04

2 votes

1 answer

234 views

Upper bound for VCdim of $H$ in terms of subgraph$(F)$, where $H := \{S(f) | f \in F\}$, with $S(f) := \{(x,y) \in X \times \{\pm 1\} | yf(x) \le 1\}$

asked Apr 23, 2022 at 19:12

1 vote

0 answers

38 views

Remove cycles from a stochastic comparison matrix, while doing the least amount of editing

asked Oct 21, 2020 at 16:19

1 vote

0 answers

32 views

Generalization bound for margin / ramp loss which is not vacuous when margin tends to zero, but recovers usual generalization bound for 0-1 loss

asked Oct 26, 2022 at 13:25

0 votes

1 answer

203 views

Construction of a collection of subsets of $\{1,2,\ldots,n\}$ with certain properties

asked Mar 15, 2023 at 7:46

0 votes

0 answers

31 views

Minimax computation for classification problems with smooth densities functions

asked May 4, 2022 at 19:33

Stack Exchange Network

9 Questions

Generate cut $(A,B)$ in edge-colored graph $(V,E_1 \cup E_2)$ such that there are more red than white crossings, i.e $|E_1(A,B)| > |E_2(A,B)|$

Strong data-processing inequality: bound $TV(T_{\#}P_0,T_{\#}P_1)$ if $\|T(x)-x\|_\infty \le \varepsilon;\forall x \in \mathbb R^p$

Worst-case complexity of computing a certain non-standard dot product + algorithms realizing this complexity

Fast private computation of dot product

Upper bound for VCdim of $H$ in terms of subgraph$(F)$, where $H := \{S(f) | f \in F\}$, with $S(f) := \{(x,y) \in X \times \{\pm 1\} | yf(x) \le 1\}$

Remove cycles from a stochastic comparison matrix, while doing the least amount of editing

Generalization bound for margin / ramp loss which is not vacuous when margin tends to zero, but recovers usual generalization bound for 0-1 loss

Construction of a collection of subsets of $\{1,2,\ldots,n\}$ with certain properties

Minimax computation for classification problems with smooth densities functions