summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorJaron Kent-Dobias <jaron@kent-dobias.com>2023-05-19 18:09:30 +0200
committerJaron Kent-Dobias <jaron@kent-dobias.com>2023-05-19 18:09:30 +0200
commitd95f3c5a3ddb04dd5d191715a467ab0db1cf60b3 (patch)
treef12369cab25a1440a6b94b8e82e5383a14e4f7aa
parent32cc4092a15298d885cabcfc738834fcea9552e4 (diff)
downloadSciPostPhys_16_001-d95f3c5a3ddb04dd5d191715a467ab0db1cf60b3.tar.gz
SciPostPhys_16_001-d95f3c5a3ddb04dd5d191715a467ab0db1cf60b3.tar.bz2
SciPostPhys_16_001-d95f3c5a3ddb04dd5d191715a467ab0db1cf60b3.zip
Computed the Franz-Parisi potential.
-rw-r--r--2-point.bib57
-rw-r--r--2-point.tex214
2 files changed, 208 insertions, 63 deletions
diff --git a/2-point.bib b/2-point.bib
index 00409af..49a5adc 100644
--- a/2-point.bib
+++ b/2-point.bib
@@ -1,3 +1,17 @@
+@article{Biroli_1999_Dynamical,
+ author = {Biroli, Giulio},
+ title = {Dynamical {TAP} approach to mean field glassy systems},
+ journal = {Journal of Physics A: Mathematical and General},
+ publisher = {IOP Publishing},
+ year = {1999},
+ month = {11},
+ number = {48},
+ volume = {32},
+ pages = {8365--8388},
+ url = {https://doi.org/10.1088%2F0305-4470%2F32%2F48%2F301},
+ doi = {10.1088/0305-4470/32/48/301}
+}
+
@article{Bray_2007_Statistics,
author = {Bray, Alan J. and Dean, David S.},
title = {Statistics of Critical Points of {Gaussian} Fields on Large-Dimensional Spaces},
@@ -12,6 +26,49 @@
doi = {10.1103/physrevlett.98.150201}
}
+@article{Folena_2020_Rethinking,
+ author = {Folena, Giampaolo and Franz, Silvio and Ricci-Tersenghi, Federico},
+ title = {Rethinking Mean-Field Glassy Dynamics and Its Relation with the Energy Landscape: The Surprising Case of the Spherical Mixed $p$-Spin Model},
+ journal = {Physical Review X},
+ publisher = {American Physical Society},
+ year = {2020},
+ month = {8},
+ volume = {10},
+ pages = {031045},
+ url = {https://link.aps.org/doi/10.1103/PhysRevX.10.031045},
+ doi = {10.1103/PhysRevX.10.031045},
+ issue = {3},
+ numpages = {26}
+}
+
+@article{Folena_2021_Gradient,
+ author = {Folena, Giampaolo and Franz, Silvio and Ricci-Tersenghi, Federico},
+ title = {Gradient descent dynamics in the mixed {$p$}-spin spherical model: finite-size simulations and comparison with mean-field integration},
+ journal = {Journal of Statistical Mechanics: Theory and Experiment},
+ publisher = {IOP Publishing},
+ year = {2021},
+ month = {3},
+ number = {3},
+ volume = {2021},
+ pages = {033302},
+ url = {https://doi.org/10.1088%2F1742-5468%2Fabe29f},
+ doi = {10.1088/1742-5468/abe29f}
+}
+
+@article{Franz_1995_Recipes,
+ author = {Franz, Silvio and Parisi, Giorgio},
+ title = {Recipes for Metastable States in Spin Glasses},
+ journal = {Journal de Physique I},
+ publisher = {EDP Sciences},
+ year = {1995},
+ month = {11},
+ number = {11},
+ volume = {5},
+ pages = {1401--1415},
+ url = {https://doi.org/10.1051%2Fjp1%3A1995201},
+ doi = {10.1051/jp1:1995201}
+}
+
@article{Ikeda_2023_Bose-Einstein-like,
author = {Ikeda, Harukuni},
title = {{Bose}--{Einstein}-like condensation of deformed random matrix: a replica approach},
diff --git a/2-point.tex b/2-point.tex
index 1c11fc1..806b4dd 100644
--- a/2-point.tex
+++ b/2-point.tex
@@ -23,22 +23,6 @@
\usepackage{tikz}
\usetikzlibrary{calc,fadings,decorations.pathreplacing,calligraphy}
-\addbibresource{2-point.bib}
-
-\begin{document}
-
-\title{
- Arrangement of nearby minima and saddles in the mixed $p$-spin energy landscape
-}
-
-\author{Jaron Kent-Dobias}
-\affil{\textsc{DynSysMath}, Istituto Nazionale di Fisica Nucleare, Sezione di Roma}
-
-\maketitle
-\begin{abstract}
-\end{abstract}
-
-
\newcommand\pgfmathsinandcos[3]{%
\pgfmathsetmacro#1{sin(#3)}%
\pgfmathsetmacro#2{cos(#3)}%
@@ -87,20 +71,50 @@
\draw[current plane,dashed] (180-\angVis:1) arc (180-\angVis:\angVis:1);
}
-%% document-wide tikz options and styles
-
\tikzset{%
>=latex, % option for nice arrows
inner sep=0pt,%
outer sep=2pt%
}
+\addbibresource{2-point.bib}
+
+\begin{document}
+
+\title{
+ Arrangement of nearby minima and saddles in the mixed spherical energy landscapes
+}
+
+\author{Jaron Kent-Dobias}
+\affil{\textsc{DynSysMath}, Istituto Nazionale di Fisica Nucleare, Sezione di Roma}
+
+\maketitle
+\begin{abstract}
+ The family of mixed spherical models was recently found to
+ violate long-held assumptions about mean-field glassy dynamics. In
+ particular, the threshold energy, where most stationary points are marginal
+ and which in the simpler pure models attracts long-time dynamics, seems to
+ loose significance. Here, we compute the typical distribution of stationary
+ points relative to each other in mixed models with a replica symmetric
+ complexity. We examine the stability of nearby points, accounting for the
+ presence of an isolated eigenvalue in their spectrum due to their proximity.
+ Despite finding rich structure not present in the pure models, we find
+ nothing that distinguishes the points that do attract the dynamics. Instead,
+ we find new geometric significance of the old threshold energy.
+\end{abstract}
+
+\tableofcontents
+
+\section{Introduction}
+
+\cite{Biroli_1999_Dynamical}
+\cite{Folena_2020_Rethinking, Folena_2021_Gradient}
\cite{Ros_2020_Distribution, Ros_2019_Complex, Ros_2019_Complexity}
\section{Model}
-The mixed $p$-spin models are defined by the Hamiltonian
+The mixed spherical models are defined by the Hamiltonian
\begin{equation} \label{eq:hamiltonian}
H(\mathbf s)=-\sum_p\frac1{p!}\sum_{i_1\cdots i_p}^NJ^{(p)}_{i_1\cdots i_p}s_{i_1}\cdots s_{i_p}
\end{equation}
@@ -138,6 +152,7 @@ The gradient and Hessian at a stationary point are then
\end{align}
where $\partial=\frac\partial{\partial\mathbf s}$ will always denote the derivative with respect to $\mathbf s$.
+\section{Results}
\section{Complexity}
@@ -209,12 +224,11 @@ Therefore, all of the Lagrange multipliers are fixed identically to the stabilit
\mathcal D(\mu)
&=\int d\lambda\,\rho(\lambda+\mu)\log|\lambda| \\
&=\begin{cases}
- \frac12+\log\left(\frac12\mu_\text m\right)+\frac\mu{\mu_\text m}\left(\frac\mu{\mu_\text m}-\sqrt{\big(\frac\mu{\mu_\text m}\big)^2-1}\right)
- -\log\left(\frac{\mu}{\mu_\text m}-\sqrt{\big(\frac\mu{\mu_\text m}\big)^2-1}\right) & \mu>\mu_\text m \\
\frac12+\log\left(\frac12\mu_\text m\right)+\frac{\mu^2}{\mu_\text m^2}
- & -\mu_\text m\leq\mu\leq\mu_\text m \\
- \frac12+\log\left(\frac12\mu_\text m\right)+\frac\mu{\mu_\text m}\left(\frac\mu{\mu_\text m}+\sqrt{\big(\frac\mu{\mu_\text m}\big)^2-1}\right)
- -\log\left(\frac{\mu}{\mu_\text m}+\sqrt{\big(\frac\mu{\mu_\text m}\big)^2-1}\right) & \mu<-\mu_\text m
+ & \mu^2\leq\mu_\text m^2 \\
+ \frac12+\log\left(\frac12\mu_\text m\right)+\frac{\mu^2}{\mu_\text m^2}
+ -\left|\frac{\mu}{\mu_\text m}\right|\sqrt{\big(\frac\mu{\mu_\text m}\big)^2-1}
+ -\log\left(\left|\frac{\mu}{\mu_\text m}\right|-\sqrt{\big(\frac\mu{\mu_\text m}\big)^2-1}\right) & \mu^2>\mu_\text m^2
\end{cases}
\end{aligned}
\end{equation}
@@ -246,11 +260,11 @@ where we have introduced the linear operator
\mathcal O(\mathbf t)
=\sum_a^m\delta(\mathbf t-\pmb\sigma_a)\left(
i\hat{\pmb\sigma}_a\cdot\partial_{\mathbf t}-\hat\beta_0
- \right)
- +
- \sum_a^n\delta(\mathbf t-\mathbf s_a)\left(
+ \right)
+ +
+ \sum_a^n\delta(\mathbf t-\mathbf s_a)\left(
i\hat{\mathbf s}_a\cdot\partial_{\mathbf t}-\hat\beta_1
- \right)
+ \right)
\end{equation}
We have written the $H$-dependant terms in this strange form for the ease of taking the average over $H$: since it is Gaussian-correlated, it follows that
\begin{equation}
@@ -307,9 +321,9 @@ where
&\quad+\frac1m\bigg\{
\frac12\sum_{ab}^m\left[
\hat\beta_1^2f(C^{00}_{ab})+(2\hat\beta_1R^{00}_{ab}-D^{00}_{ab})f'(C^{00}_{ab})+(R_{ab}^{00})^2f''(C_{ab}^{00})
- \right]+\frac12\log\det\begin{bmatrix}C^{00}&R^{00}\\R^{00}&D^{00}\end{bmatrix}
- \bigg\}
- \end{aligned}
+ \right]+\frac12\log\det\begin{bmatrix}C^{00}&R^{00}\\R^{00}&D^{00}\end{bmatrix}
+\bigg\}
+\end{aligned}
\end{equation}
is the action for the ordinary, one-point complexity, and remainder is given by
\begin{equation}
@@ -317,28 +331,28 @@ is the action for the ordinary, one-point complexity, and remainder is given by
&\mathcal S(\mathcal Q_{00},\mathcal Q_{11},\mathcal Q_{01})
=\hat\beta_1E_1-r^{11}_\mathrm d\mu_1-\frac12\hat\mu_1(1-c^{11}_\mathrm d)+\mathcal D(\mu_1) \\
&\quad+\frac1n\sum_b^n\left\{-\frac12\hat\mu_{12}(q-C^{01}_{1b})+\sum_a^m\left[
- \hat\beta_0\hat\beta_1f(C^{01}_{ab})+(\hat\beta_0R^{01}_{ab}+\hat\beta_1R^{10}_{ab}-D^{01}_{ab})f'(C^{01}_{ab})+R^{01}_{ab}R^{10}_{ab}f''(C^{01}_{ab})
- \right]\right\}
+ \hat\beta_0\hat\beta_1f(C^{01}_{ab})+(\hat\beta_0R^{01}_{ab}+\hat\beta_1R^{10}_{ab}-D^{01}_{ab})f'(C^{01}_{ab})+R^{01}_{ab}R^{10}_{ab}f''(C^{01}_{ab})
+ \right]\right\}
\\
&\quad+\frac1n\bigg\{
\frac12\sum_{ab}^n\left[
\hat\beta_1^2f(C^{11}_{ab})+(2\hat\beta_1R^{11}_{ab}-D^{11}_{ab})f'(C^{11}_{ab})+(R^{11}_{ab})^2f''(C^{11}_{ab})
\right]\\
&\quad+\frac12\log\det\left(
- \begin{bmatrix}
- C^{11}&iR^{11}\\iR^{11}&D^{11}
- \end{bmatrix}-
- \begin{bmatrix}
- C^{01}&iR^{01}\\iR^{10}&D^{01}
- \end{bmatrix}^T
- \begin{bmatrix}
- C^{00}&iR^{00}\\iR^{00}&D^{00}
- \end{bmatrix}^{-1}
- \begin{bmatrix}
- C^{01}&iR^{01}\\iR^{10}&D^{01}
- \end{bmatrix}
- \right)
- \bigg\}
+ \begin{bmatrix}
+ C^{11}&iR^{11}\\iR^{11}&D^{11}
+ \end{bmatrix}-
+ \begin{bmatrix}
+ C^{01}&iR^{01}\\iR^{10}&D^{01}
+ \end{bmatrix}^T
+ \begin{bmatrix}
+ C^{00}&iR^{00}\\iR^{00}&D^{00}
+ \end{bmatrix}^{-1}
+ \begin{bmatrix}
+ C^{01}&iR^{01}\\iR^{10}&D^{01}
+ \end{bmatrix}
+ \right)
+ \bigg\}
\end{aligned}
\end{equation}
Because of the structure of this problem in the twin limits of $m$ and $n$ to
@@ -354,7 +368,7 @@ complexities, they have the following form at the saddle point:
\begin{align}
C^{01}=
\begin{subarray}{l}
- \hphantom{[}\begin{array}{ccc}\leftarrow&n&\rightarrow\end{array}\hphantom{\Bigg]}\\
+ \hphantom{[}\begin{array}{ccc}\leftarrow&n&\rightarrow\end{array}\hphantom{\Bigg]}\\
\left[
\begin{array}{ccc}
q&\cdots&q\\
@@ -365,7 +379,7 @@ complexities, they have the following form at the saddle point:
\right]\begin{array}{c}
\\\uparrow\\m-1\\\downarrow
\end{array}
- \end{subarray}
+\end{subarray}
&&
R^{01}
=\begin{bmatrix}
@@ -415,23 +429,23 @@ then the result is
\begin{equation}
\begin{aligned}
& \begin{bmatrix}
- C^{01}&iR^{01}\\iR^{10}&D^{01}
- \end{bmatrix}^T
- \begin{bmatrix}
- C^{00}&iR^{00}\\iR^{00}&D^{00}
- \end{bmatrix}^{-1}
- \begin{bmatrix}
- C^{01}&iR^{01}\\iR^{10}&D^{01}
- \end{bmatrix} \\
- &\qquad=\begin{bmatrix}
- q^2\tilde d_\mathrm d^{00}+2qr_{10}\tilde r^{00}_\mathrm d-r_{10}^2\tilde d^{00}_\mathrm d
+ C^{01}&iR^{01}\\iR^{10}&D^{01}
+ \end{bmatrix}^T
+ \begin{bmatrix}
+ C^{00}&iR^{00}\\iR^{00}&D^{00}
+ \end{bmatrix}^{-1}
+ \begin{bmatrix}
+ C^{01}&iR^{01}\\iR^{10}&D^{01}
+ \end{bmatrix} \\
+ &\qquad=\begin{bmatrix}
+ q^2\tilde d_\mathrm d^{00}+2qr_{10}\tilde r^{00}_\mathrm d-r_{10}^2\tilde d^{00}_\mathrm d
&
i\left[d_{01}(r_{10}\tilde c^{00}_\mathrm d-q\tilde r^{00}_\mathrm d)+r_{01}(r_{10}\tilde r^{00}_\mathrm d+q\tilde d^{00}_\mathrm d)\right]
\\
i\left[d_{01}(r_{10}\tilde c^{00}_\mathrm d-q\tilde r^{00}_\mathrm d)+r_{01}(r_{10}\tilde r^{00}_\mathrm d+q\tilde d^{00}_\mathrm d)\right]
&
d_{01}^2\tilde c^{00}_\mathrm d+2r_{01}d_{01}\tilde r^{00}_\mathrm d-r_{01}^2\tilde d^{00}_\mathrm d
- \end{bmatrix}
+ \end{bmatrix}
\end{aligned}
\end{equation}
where each block is a constant $n\times n$ matrix.
@@ -451,7 +465,7 @@ point are well known, and take the values.
&=\frac1{f'(1)}
-\left(
\frac{\mu_0f(1)+\epsilon_0f'(1)}{f(1)\big(f'(1)+f''(1)\big)-f'(1)^2}
- \right)^2
+ \right)^2
\end{align}
$(r^{00}_\mathrm d)^2+d^{00}_\mathrm d=1/f'(1)$
@@ -477,13 +491,13 @@ Because the matrices $C^{00}$, $R^{00}$, and $D^{00}$ are diagonal in this case,
\\
&+\left(
(r^{01})^2-\frac{r^{11}_\mathrm d-r^{11}_0}{1-q^{11}_0}\left(2qr^{01}-\frac{(1-q^2)r^{11}_0-(q^{11}_0-q^2)r^{11}_\mathrm d}{1-q^{11}_0}\right)
- \right)\big(f'(1)-f'(q_{22}^{(0)})\big) \\
+ \right)\big(f'(1)-f'(q_{22}^{(0)})\big) \\
&+\frac{1-q^2}{1-q^{11}_0}+\frac{(r^{10}-qr^{00}_\mathrm d)^2}{1-q^{11}_0}f'(1)
-\frac1{f'(1)}\frac{f'(1)^2-f'(q)^2}{f'(1)-f'(q^{11}_0)}
+\frac{r^{11}_\mathrm d-r^{11}_0}{1-q^{11}_0}\big(r^{11}_\mathrm df'(1)-r^{11}_0f'(q^{11}_0)\big)
\\
&+\log\left(\frac{1-q_{11}^0}{f'(1)-f'(q_{11}^0)}\right)
- \Bigg\}
+ \Bigg\}
\end{aligned}
\end{equation}
@@ -508,6 +522,75 @@ Because the matrices $C^{00}$, $R^{00}$, and $D^{00}$ are diagonal in this case,
E_1=E_0+\frac12\frac{f'(1)(f'''(1)+f''(1))-f''(1)^2}{f(1)(f'(1)+f''(1))-f'(1)^2}(E_0-E_0^*)(1-q)^2+O\big((1-q)^3\big)
\end{equation}
+\section{Franz--Parisi potential}
+
+\cite{Franz_1995_Recipes}
+
+\begin{equation} \label{eq:franz-parisi.definition}
+ \beta V_\beta(q\mid E_0,\mu_0)
+ =-\frac1N\overline{\int\frac{d\nu_H(\pmb\sigma,\varsigma\mid E_0,\mu_0)}{\int d\nu_H(\pmb\sigma',\varsigma'\mid E_0,\mu_0)}\,
+ \log\bigg(\int d\mathbf s\,\delta\big(\|\mathbf s\|^2-N\big)\,\delta(\pmb\sigma\cdot\mathbf s-Nq)\,e^{-\beta H(\mathbf s)}\bigg)}
+\end{equation}
+Both the denominator and the logarithm are treated using the replica trick, which yields
+\begin{equation}
+ \beta V_\beta(q\mid E_0,\mu_0)
+ =-\frac1N\lim_{\substack{m\to0\\n\to0}}\frac\partial{\partial n}\overline{\int\left(\prod_{b=1}^md\nu_H(\pmb\sigma_b,\varsigma_b\mid E_0,\mu_0)\right)\left(\prod_{a=1}^nd\mathbf s_a\,\delta(\|\mathbf s_a\|^2-N)\,\delta(\pmb \sigma_1\cdot \mathbf s_a-Nq)\,e^{-\beta H(\mathbf s_a)}\right)}
+\end{equation}
+\begin{equation}
+ \mathcal O(\mathbf t)
+ =\sum_a^m\delta(\mathbf t-\pmb\sigma_a)\left(
+ i\hat{\pmb\sigma}_a\cdot\partial_{\mathbf t}-\hat\beta_0
+ \right)
+ -\beta
+ \sum_a^n\delta(\mathbf t-\mathbf s_a)
+\end{equation}
+\begin{equation}
+ \beta V_\beta(q\mid E_0,\mu_0)=-\frac1N\lim_{\substack{m\to0\\n\to0}}\frac\partial{\partial n}\int d\mathcal Q_0\,d\mathcal Q_1\,e^{Nm\mathcal S_0(\mathcal Q_0)+Nn\mathcal S_\mathrm{FP}(\mathcal Q_1)}
+\end{equation}
+
+\begin{equation}
+ n\mathcal S_{\mathrm{FP}}
+ =\frac12\beta^2\sum_{ab}^nf(Q_{ab})
+ +\beta\sum_a^m\sum_b^n\left[
+ \hat\beta_0f(C^{01}_{ab})
+ +R^{10}_{ab}f'(C^{01}_{ab})
+ \right]
+ +\frac12\log\det\left(
+ Q-\begin{bmatrix}C^{01}\\iR^{10}\end{bmatrix}^T\begin{bmatrix}C^{00}&iR^{00}\\iR^{00}&D^{00}\end{bmatrix}^{-1}\begin{bmatrix}C^{01}\\iR^{10}\end{bmatrix}
+ \right)
+\end{equation}
+
+\begin{equation}
+ \begin{aligned}
+ \beta V_\beta&=\frac12\beta^2\big[f(1)-(1-x)f(q_1)-xf(q_0)\big]
+ +\beta\hat\beta_0f(q)+\beta r^{10}f'(q)-\frac{1-x}x\log(1-q_1)
+ +\frac1x\log(1-(1-x)q_1-xq_0) \\
+ &+\frac{q_0-d^{00}_df'(1)q^2-2r^{00}_df'(1)r^{10}q+(r^{10})^2f'(1)}{
+ 1-(1-x)q_1-xq_0
+ }
+ \end{aligned}
+\end{equation}
+The saddle point for $r^{10}$ can be taken explicitly. After this, we take the
+limit of $\beta\to\infty$. There are two possibilities. First, in the replica
+symmetric case $x=1$, and in the limit of large $\beta$ $q_0$ will scale like
+$q_0=1-(y_0\beta)^{-1}$. Inserting this, the limit is
+\begin{equation}
+ V_\infty=-\hat\beta_0 f(q)-r^{11}_\mathrm df'(q)q-\frac12\left(y_0(1-q^2)+\frac{f'(1)^2-f'(q)^2}{y_0f'(1)}\right)
+\end{equation}
+The saddle point in $y_0$ can now be taken, taking care to choose the solution for $y_0>0$. This gives
+\begin{equation}
+ V_0^{\textsc{rs}}=-\hat\beta_0f(q)-r^{11}_\mathrm df'(q)q-\sqrt{(1-q^2)\left(1-\frac{f'(q)^2}{f'(1)^2}\right)}
+\end{equation}
+The second case is when the inner statistical mechanics problem has replica symmetry breaking. Here, $q_0$ approaches a nontrivial limit, but $x=z\beta^{-1}$ approaches zero and $q_1=1-(y_1\beta)^{-1}$ approaches one.
+\begin{equation}
+ V_0^{\oldstylenums{1}\textsc{rsb}}=-\hat\beta_0f(q)-r^{11}_\mathrm df'(q)q-\frac12\left(
+ z(f(1)-f(q_0))+\frac{f'(1)}{y_1}-\frac{y_1(q^2-q_0)}{1+y_1z(1-q_0)}-(1+y_0z(1-q_0))\frac{f'(q)^2}{y_1f'(1)}+\frac1z\log\left(1+zy_1(1-q_0)\right)
+ \right)
+\end{equation}
+Though the saddle point in $y_1$ can technically be evaluated in this
+expression, it delivers no insight. The final potential is found by taking the
+saddle over $z$, $y_1$, and $q_0$.
+
\section{Isolated eigenvalue}
The two-point complexity depends on the spectrum at both stationary points
@@ -1031,6 +1114,11 @@ assuming the last equation is satisfied. The trivial solution, which gives the b
\]
as expected. We need to first the nontrivial solutions with nonzero $X$, but because the coefficients are so nasty this will be a numeric problem... Specifically, we are good for $y$ where one of the eigenvalues of $B-yC$ is zero.
+\section{Conclusion}
+
+The methods developed in this paper are straightforwardly (if not easily)
+generalized to landscapes with replica symmetry broken complexities.
+
\paragraph{Acknowledgements}
\paragraph{Funding information}