Using precise random matrix theory tools and the Kac–Rice formula, we provide sharp O(1) asymptotics for the average number of deep minima of the (p, k) spiked tensor model. These sharp estimates allow us to prove that, when the signal-to-noise ratio is large enough, the expected number of deep minima is asymptotically finite as N tends to infinity and to establish the occurrence of topological trivialization by showing that this number vanishes when the strength of the signal-to-noise ratio diverges. We also derive an explicit formula for the value of the absolute minimum (the limiting ground state energy) on the N-dimensional sphere, similar to the recent work of Jagannath, Lopatto, and Miolane [Ann. Appl. Probab. 4, 1910–1933 (2020)].

1.
Adler
,
R. J.
and
Taylor
,
J. E.
,
Random Fields and Geometry
, Springer Monographs in Mathematics (
Springer-Verlag
,
New York
,
2007
).
2.
Auffinger
,
A.
and
Ben Arous
,
G.
, “
Complexity of random smooth functions on the high-dimensional sphere
,”
Ann. Probab.
41
(
6
),
4214
4247
(
2013
).
3.
Auffinger
,
A.
,
Ben Arous
,
G.
, and
Černý
,
J.
, “
Random matrices and complexity of spin glasses
,”
Commun. Pure Appl. Math.
66
(
2
),
165
201
(
2013
).
4.
Azaïs
,
J.-M.
and
Wschebor
,
M.
,
Level Sets and Extrema of Random Processes and Fields
(
John Wiley & Sons, Inc.
,
Hoboken, NJ
,
2009
).
5.
Belius
,
D.
,
Černý
,
J.
,
Nakajima
,
S.
, and
Schmidt
,
M.
, “
Triviality of the geometry of mixed p-spin spherical Hamiltonians with external field
,”
J. Stat. Phys.
186
,
12
(
2021
).
6.
Ben Arous
,
G.
and
Guionnet
,
A.
, “
Large deviations for Wigner’s law and Voiculescu’s non-commutative entropy
,”
Probab. Theory Relat. Fields
108
(
4
),
517
542
(
1997
).
7.
Ben Arous
,
G.
,
Mei
,
S.
,
Montanari
,
A.
, and
Nica
,
M.
, “
The landscape of the spiked tensor model
,”
Commun. Pure Appl. Math.
72
(
11
),
2282
2330
(
2019
).
8.
Benaych-Georges
,
F.
,
Guionnet
,
A.
, and
Maida
,
M.
, “
Large deviations of the extreme eigenvalues of random deformations of matrices
,”
Probab. Theory Relat. Fields
154
(
3
),
703
751
(
2012
).
9.
Cavagna
,
A.
,
Garrahan
,
J. P.
, and
Giardina
,
I.
, “
Quenched complexity of the mean-field p-spin spherical model with external magnetic field
,”
J. Phys. A: Math. Gen.
32
(
5
),
711
723
(
1999
).
10.
Cavagna
,
A.
,
Giardina
,
I.
, and
Parisi
,
G.
, “
Stationary points of the Thouless-Anderson-Palmer free energy
,”
Phys. Rev. B
57
,
11251
11257
(
1998
).
11.
Chen
,
W.-K.
, “
Phase transition in the spiked random tensor with Rademacher prior
,”
Ann. Stat.
47
(
5
),
2734
2756
(
2019
).
12.
Chen
,
W.-K.
and
Sen
,
A.
, “
Parisi formula, disorder chaos and fluctuation for the ground state energy in the spherical mixed p-spin models
,”
Commun. Math. Phys.
350
,
129
(
2015
).
13.
Desrosiers
,
P.
and
Liu
,
D.-Z.
, “
Scaling limits of correlations of characteristic polynomials for the Gaussian β-ensemble with external source
,”
Int. Math. Res. Not.
12
,
3751
3781
(
2015
).
14.
Fyodorov
,
Y. V.
, “
High-dimensional random fields and random matrix theory
,”
Markov Processes Relat. Fields
21
,
483
518
(
2013
).
15.
Fyodorov
,
Y. V.
, “
Topology trivialization transition in random non-gradient autonomous ODEs on a sphere
,”
J. Stat. Mech.: Theory Exp.
2016
(
12
),
124003
.
16.
Fyodorov
,
Y. V.
and
Le Doussal
,
P.
, “
Topology trivialization and large deviations for the minimum in the simplest random optimization
,”
J. Stat. Phys.
154
(
1
),
466
490
(
2014
).
17.
Gillin
,
P.
and
Sherrington
,
D.
, “
p > 2 spin glasses with first-order ferromagnetic transitions
,”
J. Phys. A: Math. Gen.
33
(
16
),
3081
3091
(
2000
).
18.
Jagannath
,
A.
,
Lopatto
,
P.
, and
Miolane
,
L.
, “
Statistical thresholds for tensor PCA
,”
Ann. Appl. Probab.
30
(
4
),
1910
1933
(
2020
).
19.
Jagannath
,
A.
and
Tobasco
,
I.
, “
Low temperature asymptotics of spherical mean field spin glasses
,”
Commun. Math. Phys.
352
(
3
),
979
1017
(
2017
).
20.
Maillard
,
A.
,
Ben Arous
,
G.
, and
Biroli
,
G.
, “
Landscape complexity for the empirical risk of generalized linear models
,” in
Proceedings of the First Mathematical and Scientific Machine Learning Conference, Proceedings of Machine Learning Research (PMLR)
, edited by
Lu
,
J.
and
Ward
,
R.
(
Princeton University
,
Princeton, NJ
,
2020
), Vol. 107, pp.
287
327
.
21.
Mannelli
,
S. S.
,
Krzakala
,
F.
,
Urbani
,
P.
, and
Zdeborová
,
L.
, “
Passed and spurious: Descent algorithms and local minima in spiked matrix-tensor models
,” in
PMLR
, edited by
Chaudhuri
,
K.
and
Salakhutdinov
,
R.
(
Proceedings of Machine Learning Research
, 2019), Vol. 97, pp.
4333
4342
.
22.
Montanari
,
A.
and
Richard
,
E.
, “
A statistical model for tensor PCA
,” in
Proceedings of the 27th International Conference on Neural Information Processing Systems
(
online
,
2014
), Vol. 2, pp.
2897
2905
.
23.
Perry
,
A.
,
Wein
,
A. S.
, and
Bandeira
,
A. S.
, “
Statistical limits of spiked tensor models
,”
Ann. Inst. Henri Poincare: Probab. Stat.
56
(
1
),
230
264
(
2020
).
24.
Ros
,
V.
,
Ben Arous
,
G.
,
Biroli
,
G.
, and
Cammarota
,
C.
, “
Complex energy landscapes in spiked-tensor and simple glassy models: Ruggedness, arrangements of local minima, and phase transitions
,”
Phys. Rev. X
9
,
011003
(
2019
).
25.
Sarao Mannelli
,
S.
,
Biroli
,
G.
,
Cammarota
,
C.
,
Krzakala
,
F.
,
Urbani
,
P.
, and
Zdeborová
,
L.
, “
Marvels and pitfalls of the Langevin algorithm in noisy high-dimensional inference
,”
Phys. Rev. X
10
,
011057
(
2020
).
26.
Sarao Mannelli
,
S.
,
Biroli
,
G.
,
Cammarota
,
C.
,
Krzakala
,
F.
, and
Zdeborová
,
L.
, “
Who is afraid of big bad minima? Analysis of gradient-flow in spiked matrix-tensor models
,” in
Advances in Neural Information Processing Systems
(
Curran Associates, Inc.
,
2019
), Vol. 32, pp.
8679
8689
.
You do not currently have access to this content.