This paper gives two kinds of functions for which Uesaka's Conjecture, stating that the globally optimum (not a local minimum) of a quadratic function F(x)=-(1/2)xtAx in the n-dimensional hypercube may be obtained by solving a differential equation, holds true, where n denotes the dimension of the vector x. Uesaka stated in his paper that he proved the conjecture only for n=2. This corresponds to a very special case of this paper. The results of this paper suggest that the conjecture really holds for a wide class of quadratic functions and therefore support the conjecture partially.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Tetsuo NISHI, "On the Uesaka's Conjecture as to the Optimization by Means of Neural Networks for Combinatorial Problems" in IEICE TRANSACTIONS on Fundamentals,
vol. E81-A, no. 9, pp. 1811-1817, September 1998, doi: .
Abstract: This paper gives two kinds of functions for which Uesaka's Conjecture, stating that the globally optimum (not a local minimum) of a quadratic function F(x)=-(1/2)xtAx in the n-dimensional hypercube may be obtained by solving a differential equation, holds true, where n denotes the dimension of the vector x. Uesaka stated in his paper that he proved the conjecture only for n=2. This corresponds to a very special case of this paper. The results of this paper suggest that the conjecture really holds for a wide class of quadratic functions and therefore support the conjecture partially.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e81-a_9_1811/_p
Copy
@ARTICLE{e81-a_9_1811,
author={Tetsuo NISHI, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={On the Uesaka's Conjecture as to the Optimization by Means of Neural Networks for Combinatorial Problems},
year={1998},
volume={E81-A},
number={9},
pages={1811-1817},
abstract={This paper gives two kinds of functions for which Uesaka's Conjecture, stating that the globally optimum (not a local minimum) of a quadratic function F(x)=-(1/2)xtAx in the n-dimensional hypercube may be obtained by solving a differential equation, holds true, where n denotes the dimension of the vector x. Uesaka stated in his paper that he proved the conjecture only for n=2. This corresponds to a very special case of this paper. The results of this paper suggest that the conjecture really holds for a wide class of quadratic functions and therefore support the conjecture partially.},
keywords={},
doi={},
ISSN={},
month={September},}
Copy
TY - JOUR
TI - On the Uesaka's Conjecture as to the Optimization by Means of Neural Networks for Combinatorial Problems
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1811
EP - 1817
AU - Tetsuo NISHI
PY - 1998
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E81-A
IS - 9
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - September 1998
AB - This paper gives two kinds of functions for which Uesaka's Conjecture, stating that the globally optimum (not a local minimum) of a quadratic function F(x)=-(1/2)xtAx in the n-dimensional hypercube may be obtained by solving a differential equation, holds true, where n denotes the dimension of the vector x. Uesaka stated in his paper that he proved the conjecture only for n=2. This corresponds to a very special case of this paper. The results of this paper suggest that the conjecture really holds for a wide class of quadratic functions and therefore support the conjecture partially.
ER -