Searcharxiv⌕ Search

arXiv subjects

Matthias Löwe

Publications and source records attributed to Matthias Löwe.

At least 37 records · Page 2Linked to original sources
arXiv2020

A Central Limit Theorem for the mean starting hitting time for a random walk on a random graph

We consider simple random walk on a realization of an Erdős-Rényi graph that is asymptotically almost surely (a.a.s.) connected. We show a Central Limit Theorem (CLT) for the average starting hitting time, i.e. the expected time it takes the random walker on average to first hit a vertex $j$ when starting in a fixed vertex $i$. The average is taken with respect to $π_j$, the invariant measure of the random walk.

math.PR↗
arXiv2020

A Central Limit Theorem for incomplete U-statistics over triangular arrays

We analyze the fluctuations of incomplete $U$-statistics over a triangular array of independent random variables. We give criteria for a Central Limit Theorem (CLT, for short) to hold in the sense that we prove that an appropriately scaled and centered version of the U-statistic converges to a normal random variable. Our method of proof relies on a martingale CLT. A possible application -- a CLT for the hitting time for random walk on random graphs -- will be presented in \cite{LoTe20b}

math.PR↗
arXiv2020

Fluctuation results for general block spin Ising models

We study a block spin mean-field Ising model, i.e. a model of spins in which the vertices are divided into a finite number of blocks with each block having a fixed proportion of vertices, and where pair interactions are given according to their blocks. For the vector of block magnetizations we prove Large Deviation Principles and Central Limit Theorems under general assumptions for the block interaction matrix. Using the exchangeable pair approach of Stein's method we establish a rate of convergence in the Central Limit Theorem for the block magnetization vector in the high temperature regime.

math.PR↗
arXiv2020

Multi-group Binary Choice with Social Interaction and a Random Communication Structure -- a Random Graph Approach

We construct and analyze a random graph model for discrete choice with social interaction and several groups of equal size. We concentrate on the case of two groups of equal sizes and we allow the interaction strength within a group to differ from the interaction strength between the two groups. Given that the resulting graph is sufficiently dense we show that, with probability one, the average decision in each of the two groups is the same as in the fully connected model. In particular, we show that there is a phase transition: If the interaction among a group and between the groups is strong enough the average decision per group will either be positive or negative and the decision of the two groups will be correlated. We also compute the free energy per particle in our model.

math.PR↗
arXiv2020

Fluctuations for block spin Ising models

We analyze the high temperature fluctuations of the magnetization of the so-called Ising block model. This model was recently introduced by Berthet, Rigollet and Srivastava. We prove a Central Limit Theorems (CLT) for the magnetization in the high temperature regime. At the same time we show that this CLT breaks down at a line of critical temperatures. At this line we show the validity of a non-standard Central Limit Theorems for the magnetization.

math.PR↗
arXiv2020

Exact Recovery in Block Spin Ising Models at the Critical Line

We show how to exactly reconstruct the block structure at the critical line in the so-called Ising block model. This model was re-introduced by Berthet, Rigollet and Srivastava in a recent paper. There the authors show how to exactly reconstruct blocks away from the critical line and they give an upper and a lower bound on the number of observations one needs; thereby they establish a minimax optimal rate (up to constants). Our technique relies on a combination of their methods with fluctuation results for block spin Ising models. The latter are extended to the full critical regime. We find that the number of necessary observations depends on whether the interaction parameter between two blocks is positive or negative: In the first case, there are about $N \log N$ observations required to exactly recover the block structure, while in the latter $\sqrt N \log N$ observations suffice.

math.PR↗
arXiv2020

Fluctuations for the partition function of Ising models on Erdös-Rényi random graphs

We analyze Ising/Curie-Weiss models on the Erdős-Rényi graph with $N$ vertices and edge probability $p=p(N)$ that were introduced by Bovier and Gayrard [J.\ Statist.\ Phys., 72(3-4):643--664, 1993] and investigated in two previous articles by the authors. We prove Central Limit Theorems for the partition function of the model and -- at other decay regimes of $p(N)$ -- for the logarithmic partition function. We find critical regimes for $p(N)$ at which the behavior of the fluctuations of the partition function changes.

math.PR↗
arXiv2020

Equi-Energy sampling does not converge rapidly on the mean-field Potts model with three colors close to the critical temperature

Equi-Energy Sampling (EES, for short) is a method to speed up the convergence of the Metropolis chain, when the latter is slow. We show that there are still models like the mean-field Potts model, where EES does not converge rapidly in certain temperature regimes. Indeed we will show that EES is slowly mixing on the mean-field Potts model, in a regime below the critical temperature. Though we will concentrate on the Potts model with three colors, our arguments remain valid for any number of colors $q \ge 3$, if we adapt the temperature regime. For the situation of the mean-field Potts model this answers a question posed in \cite{HuaKou}.

math.PR↗
arXiv2019

Fluctuations of the Magnetization for Ising Models on Erdős-Rényi Random Graphs -- the Regimes of Small p and the Critical Temperature

We continue our analysis of Ising models on the (directed) Erdős-Rényi random graph. This graph is constructed on $N$ vertices and every edge has probability $p$ to be present. These models were introduced by Bovier and Gayrard [J. Stat. Phys., 1993] and analyzed by the authors in a previous note, in which we consider the case of $p=p(N)$ satisfying $p^3N^2\to +\infty$ and $β<1$. In the current note we prove a quenched Central Limit Theorem for the magnetization for $p$ satisfying $pN \to \infty$ in the high-temperature regime $β<1$. We also show a non-standard Central Limit Theorem for $p^4N^3 \to \infty$ at the critical temperature $β=1$. For $p^4N^3 \to 0$ we obtain a Gaussian limiting distribution for the magnetization. Finally, on the critical line $p^4N^3 \to c$ the limiting distribution for the magnetization contains a quadratic component as well as a $x^4$-term. Hence, at $β=1$ we observe a phase transition in $p$ for the fluctuations of the magnetization.

math.PR↗
arXiv2019

Moderate deviations for the size of the giant component in a random hypergraph

We prove a moderate deviations principles for the size of the largest connected component in a random $d$-uniform hypergraph. The key tool is a version of the exploration process, that is also used to investigate the giant component of an Erdös-Rényi graph, a moderate deviations principle for the martingale associated with this exploration process, and exponential estimates.

math.PR↗
arXiv2019

Fluctuations of the Magnetization for Ising Models on Dense Erdős-Rényi Random Graphs

We analyze Ising/Curie-Weiss models on the (directed) Erdős-Rényi random graph on $N$ vertices in which every edge is present with probability $p$. These models were introduced by Bovier and Gayrard [J. Stat. Phys., 1993]. We prove a quenched Central Limit Theorem for the magnetization in the high-temperature regime $β<1$ when $p=p(N)$ satisfies $p^3N^2\to +\infty$.

math.PR↗
arXiv2019

The semicircle law for matrices with ergodic entries

We study the empirical spectral distribution (ESD) of symmetric random matrices with ergodic entries on the diagonals. We observe that for entries with correlations that decay to 0, when the distance of the diagonal entries becomes large the limiting ESD is the well known semicircle law. If it does not decay to 0 (and have the same sign) the semicircle law cannot be the limit of the ESD. This is good agreement with results on exchangeable processes analysed in Friesen and Löwe (2013a) and Hochstättler et al. (2016).

math.PR↗
arXiv2018

Lindeberg's method for moderate deviations and random summation

We apply Lindeberg's method, invented to prove a central limit theorem, to analyze the moderate deviations around such a central limit theorem. In particular, we will show moderate deviation principles for martingales as well as for random sums, in the latter situation both, in the case when the limit distribution is Gaussian or non-Gaussian. Moreover in the Gaussian case we show moderate deviations for random sums using bounds on cumulants, alternatively. Finally, we also prove a large deviation principle for certain random sums.

math.PR↗
arXiv2017

The sparse Blume-Emery-Griffiths model of associative memories

We analyze the Blume-Emery-Griffiths (BEG) associative memory with sparse patterns and at zero temperature. We give bounds on its storage capacity provided that we want the stored patterns to be fixed points of the retrieval dynamics. We compare our results to that of other models of sparse neural networks and show that the BEG model has a superior performance compared to them.

math.PR↗
arXiv2017

Improving Accuracy of Nonparametric Transfer Learning via Vector Segmentation

Transfer learning using deep neural networks as feature extractors has become increasingly popular over the past few years. It allows to obtain state-of-the-art accuracy on datasets too small to train a deep neural network on its own, and it provides cutting edge descriptors that, combined with nonparametric learning methods, allow rapid and flexible deployment of performing solutions in computationally restricted settings. In this paper, we are interested in showing that the features extracted using deep neural networks have specific properties which can be used to improve accuracy of downstream nonparametric learning methods. Namely, we demonstrate that for some distributions where information is embedded in a few coordinates, segmenting feature vectors can lead to better accuracy. We show how this model can be applied to real datasets by performing experiments using three mainstream deep neural network feature extractors and four databases, in vision and audio.

cs.LG↗
arXiv2017

Associative Memories to Accelerate Approximate Nearest Neighbor Search

Nearest neighbor search is a very active field in machine learning for it appears in many application cases, including classification and object retrieval. In its canonical version, the complexity of the search is linear with both the dimension and the cardinal of the collection of vectors the search is performed in. Recently many works have focused on reducing the dimension of vectors using quantization techniques or hashing, while providing an approximate result. In this paper we focus instead on tackling the cardinal of the collection of vectors. Namely, we introduce a technique that partitions the collection of vectors and stores each part in its own associative memory. When a query vector is given to the system, associative memories are polled to identify which one contain the closest match. Then an exhaustive search is conducted only on the part of vectors stored in the selected associative memory. We study the effectiveness of the system when messages to store are generated from i.i.d. uniform $\pm$1 random variables or 0-1 sparse i.i.d. random variables. We also conduct experiment on both synthetic data and real data and show it is possible to achieve interesting trade-offs between complexity and accuracy.

cs.LG↗
arXiv2017

On a model of associative memory with huge storage capacity

In [7] Krotov and Hopfield suggest a generalized version of the well-known Hopfield model of associative memory. In their version they consider a polynomial interaction function and claim that this increases the storage capacity of the model. We prove this claim and take the "limit" as the degree of the polynomial becomes infinite, i.e. an exponential interaction function. With this interaction we prove that model has an exponential storage capacity in the number of neurons, yet the basins of attraction are almost as large as in the standard Hopfield model.

math.PR↗