Results 181 to 190 of about 26,379 (227)
A New Paradigm for Generative Adversarial Networks based on Randomized Decision Rules. [PDF]
Stat SinKim S, Song Q, Liang F.
europepmc +1 more source
Assessing the association of type 2 diabetes with skin health status: a study of the Northern Finland Birth Cohort 1966. [PDF]
BMJ OpenNasserinejad M +6 more
europepmc +1 more source
A dataset of gameplay videos with frame-wise board annotations, piece annotations, and state mappings for the Connect Four game. [PDF]
Data BriefG PK, M L A, M N AK.
europepmc +1 more source
Exactly solvable statistical physics models for large neuronal populations. [PDF]
Phys Rev ResLynn CW +4 more
europepmc +1 more source
Empirical Entropy, Minimax Regret and Minimax Risk [PDF]
Bernoulli, 2017 We consider the random design regression model with square loss. We propose a method that aggregates empirical minimizers (ERM) over appropriately chosen random subsets and reduces to ERM in the extreme case, and we establish sharp oracle inequalities for its risk. We show that, under the $\varepsilon^{-p}$ growth of the empirical $\varepsilon$-entropy,
Alexander Rakhlin +2 more
exaly +5 more sources
Some of the next articles are maybe not open access.
Related searches:
Related searches:
Mathematical Notes of the Academy of Sciences of the USSR, 1991
The minimax equality \[ \inf_{t\in T}\sup_{x\in X}f(t,x) = \sup_{x\in X}\inf_{t\in T}f(t,x) \] is established in a non-standard case. Here \(T\) is a compact subinterval of the real line, but \(X\) is a compact metric space and the continuous function \(f\) is \(t\)-convex on \(T\) and satisfies a ``global maximum'' \(x\)-condition on \(X\).
Borenshteĭn, O. Yu., Shul'man, V. S.
openaire +1 more source
The minimax equality \[ \inf_{t\in T}\sup_{x\in X}f(t,x) = \sup_{x\in X}\inf_{t\in T}f(t,x) \] is established in a non-standard case. Here \(T\) is a compact subinterval of the real line, but \(X\) is a compact metric space and the continuous function \(f\) is \(t\)-convex on \(T\) and satisfies a ``global maximum'' \(x\)-condition on \(X\).
Borenshteĭn, O. Yu., Shul'man, V. S.
openaire +1 more source
Mathematics of Operations Research, 1984
A new, general criterion is given for ensuring that a closed saddle function has a nonempty compact set of saddlepoints. Under this criterion it is shown also that every minimaximizing sequence clusters around some saddlepoint. A comparable theorem is given for semicontinuous quasi-saddle functions.
openaire +3 more sources
A new, general criterion is given for ensuring that a closed saddle function has a nonempty compact set of saddlepoints. Under this criterion it is shown also that every minimaximizing sequence clusters around some saddlepoint. A comparable theorem is given for semicontinuous quasi-saddle functions.
openaire +3 more sources
SIAM Journal on Computing, 1985
This paper concerns the following problem. Given vertices $v_1 , \cdots ,v_n $ with weights $w_1 , \cdots ,w_n $, construct a t-ary tree with leaves $v_1 , \cdots ,v_n $ in left to right order, such that if $l_i $ denotes the length of the path from $v_i $ to the root for each i, the maximum of $w_i + l_i $ is minimized. A linear algorithm is presented
David G. Kirkpatrick, Maria M. Klawe
openaire +3 more sources
This paper concerns the following problem. Given vertices $v_1 , \cdots ,v_n $ with weights $w_1 , \cdots ,w_n $, construct a t-ary tree with leaves $v_1 , \cdots ,v_n $ in left to right order, such that if $l_i $ denotes the length of the path from $v_i $ to the root for each i, the maximum of $w_i + l_i $ is minimized. A linear algorithm is presented
David G. Kirkpatrick, Maria M. Klawe
openaire +3 more sources