arXiv subjects

H. J. Kappen

Publications and source records attributed to H. J. Kappen.

16 recordsLinked to original sources

arXiv2023

Efficient inference in the transverse field Ising model

In this paper we introduce an approximate method to solve the quantum cavity equations for transverse field Ising models. The method relies on a projective approximation of the exact cavity distributions of imaginary time trajectories (paths). A key feature, novel in the context of similar algorithms, is the explicit separation of the classical and quantum parts of the distributions. Numerical simulations show accurate results in comparison with the sampled solution of the cavity equations, the exact diagonalization of the Hamiltonian (when possible) and other approximate inference methods in the literature. The computational complexity of this new algorithm scales linearly with the connectivity of the underlying lattice, enabling the study of highly connected networks, as the ones often encountered in quantum machine learning problems.

cond-mat.dis-nn↗

arXiv2019

Implementing perceptron models with qubits

We propose a method for learning a quantum probabilistic model of a perceptron. By considering a cross entropy between two density matrices we can learn a model that takes noisy output labels into account while learning. A multitude of proposals already exist that aim to utilize the curious properties of quantum systems to build a quantum perceptron, but these proposals rely on a classical cost function for the optimization procedure. We demonstrate the usage of a quantum equivalent of the classical log-likelihood, which allows for a quantum model and training procedure. We show that this allows us to better capture noisyness in data compared to a classical perceptron. By considering entangled qubits we can learn nonlinear separation boundaries, such as XOR.

quant-ph↗

arXiv2018

Consistent Adaptive Multiple Importance Sampling and Controlled Diffusions

Recent progress has been made with Adaptive Multiple Importance Sampling (AMIS) methods that show improvement in effective sample size. However, consistency for the AMIS estimator has only been established in very restricted cases. Furthermore, the high computational complexity of the re-weighting in AMIS (called balance heuristic) makes it expensive for applications involving diffusion processes. In this work we consider sequential and adaptive importance sampling that is particularly suitable for diffusion processes. We propose a new discarding-re-weighting scheme that is of lower computational complexity, and we prove that the resulting AMIS is consistent. Using numerical experiments, we demonstrate that discarding-re-weighting performs very similar to the balance heuristic, but at a fraction of the computational cost.

math.OC↗

arXiv2018

Effective Connectivity from Single Trial fMRI Data by Sampling Biologically Plausible Models

The estimation of causal network architectures in the brain is fundamental for understanding cognitive information processes. However, access to the dynamic processes underlying cognition is limited to indirect measurements of the hidden neuronal activity, for instance through fMRI data. Thus, estimating the network structure of the underlying process is challenging. In this article, we embed an adaptive importance sampler called Adaptive Path Integral Smoother (APIS) into the Expectation-Maximization algorithm to obtain point estimates of causal connectivity. We demonstrate on synthetic data that this procedure finds not only the correct network structure but also the direction of effective connections from random initializations of the connectivity matrix. In addition--motivated by contradictory claims in the literature--we examine the effect of the neuronal timescale on the sensitivity of the BOLD signal to changes in the connectivity and on the maximum likelihood solutions of the connectivity. We conclude with two warnings: First, the connectivity estimates under the assumption of slow dynamics can be extremely biased if the data was generated by fast neuronal processes. Second, the faster the time scale, the less sensitive the BOLD signal is to changes in the incoming connections to a node. Hence, connectivity estimation using realistic neural dynamics timescale requires extremely high-quality data and seems infeasible in many practical data sets.

q-bio.NC↗

arXiv2017

Particle Smoothing for Hidden Diffusion Processes: Adaptive Path Integral Smoother

Particle smoothing methods are used for inference of stochastic processes based on noisy observations. Typically, the estimation of the marginal posterior distribution given all observations is cumbersome and computational intensive. In this paper, we propose a simple algorithm based on path integral control theory to estimate the smoothing distribution of continuous-time diffusion processes with partial observations. In particular, we use an adaptive importance sampling method to improve the effective sampling size of the posterior over processes given the observations and the reliability of the estimation of the marginals. This is achieved by estimating a feedback controller to sample efficiently from the joint smoothing distributions. We compare the results with estimations obtained from the standard Forward Filter/Backward Simulator for two diffusion processes of different complexity. We show that the proposed method gives more reliable estimations than the standard FFBSi when the smoothing distribution is poorly represented by the filter distribution.

cs.LG↗

arXiv2016

Path Integral Control and State Dependent Feedback

In this paper we address the problem to compute state dependent feedback controls for path integral control problems. To this end we generalize the path integral control formula and utilize this to construct parameterized state dependent feedback controllers. In addition, we show a novel relation between control and importance sampling: better control, in terms of control cost, yields more efficient importance sampling, in terms of effective sample size. The optimal control provides a zero-variance estimate.

math.OC↗

arXiv2013

Comment: Causal entropic forces

In this comment I argue that the causal entropy proposed in [1] is state-independent and the entropic force is zero for state-independent noise in a discrete time formulation and that the causal entropy description is incomplete in the continuous time case.

cond-mat.stat-mech↗

arXiv2009

Approximate inference on planar graphs using Loop Calculus and Belief Propagation

We introduce novel results for approximate inference on planar graphical models using the loop calculus framework. The loop calculus (Chertkov and Chernyak, 2006) allows to express the exact partition function of a graphical model as a finite sum of terms that can be evaluated once the belief propagation (BP) solution is known. In general, full summation over all correction terms is intractable. We develop an algorithm for the approach presented in (Certkov et al., 2008) which represents an efficient truncation scheme on planar graphs and a new representation of the series in terms of Pfaffians of matrices. We analyze the performance of the algorithm for the partition function approximation for models with binary variables and pairwise interactions on grids and other planar graphs. We study in detail both the loop series and the equivalent Pfaffian series and show that the first term of the Pfaffian series for the general, intractable planar model, can provide very accurate approximations. The algorithm outperforms previous truncation schemes of the loop series and is competitive with other state-of-the-art methods for approximate inference.

cs.AI↗

arXiv2007

Truncating the loop series expansion for Belief Propagation

Recently, M. Chertkov and V.Y. Chernyak derived an exact expression for the partition sum (normalization constant) corresponding to a graphical model, which is an expansion around the Belief Propagation solution. By adding correction terms to the BP free energy, one for each "generalized loop" in the factor graph, the exact partition sum is obtained. However, the usually enormous number of generalized loops generally prohibits summation over all correction terms. In this article we introduce Truncated Loop Series BP (TLSBP), a particular way of truncating the loop series of M. Chertkov and V.Y. Chernyak by considering generalized loops as compositions of simple loops. We analyze the performance of TLSBP in different scenarios, including the Ising model, regular random graphs and on Promedas, a large probabilistic medical diagnostic system. We show that TLSBP often improves upon the accuracy of the BP solution, at the expense of increased computation time. We also show that the performance of TLSBP strongly depends on the degree of interaction between the variables. For weak interactions, truncating the series leads to significant improvements, whereas for strong interactions it can be ineffective, even if a high number of terms is considered.

cs.AI↗

arXiv2007

On Cavity Approximations for Graphical Models

We reformulate the Cavity Approximation (CA), a class of algorithms recently introduced for improving the Bethe approximation estimates of marginals in graphical models. In our new formulation, which allows for the treatment of multivalued variables, a further generalization to factor graphs with arbitrary order of interaction factors is explicitly carried out, and a message passing algorithm that implements the first order correction to the Bethe approximation is described. Furthermore we investigate an implementation of the CA for pairwise interactions. In all cases considered we could confirm that CA[k] with increasing $k$ provides a sequence of approximations of markedly increasing precision. Furthermore in some cases we could also confirm the general expectation that the approximation of order $k$, whose computational complexity is $O(N^{k+1})$ has an error that scales as $1/N^{k+1}$ with the size of the system. We discuss the relation between this approach and some recent developments in the field.

cond-mat.stat-mech↗

arXiv2006

Competition between synaptic depression and facilitation in attractor neural networks

We study the effect of competition between short-term synaptic depression and facilitation on the dynamical properties of attractor neural networks, using Monte Carlo simulation and a mean field analysis. Depending on the balance between depression, facilitation and the noise, the network displays different behaviours, including associative memory and switching of the activity between different attractors. We conclude that synaptic facilitation enhances the attractor instability in a way that (i) intensifies the system adaptability to external stimuli, which is in agreement with experiments, and (ii) favours the retrieval of information with less error during short--time intervals.

q-bio.NC↗

arXiv2006

Algorithms for identification and categorization

The main features of a family of efficient algorithms for recognition and classification of complex patterns are briefly reviewed. They are inspired in the observation that fast synaptic noise is essential for some of the processing of information in the brain.

q-bio.NC↗

arXiv2005

Path integrals and symmetry breaking for optimal control theory

This paper considers linear-quadratic control of a non-linear dynamical system subject to arbitrary cost. I show that for this class of stochastic control problems the non-linear Hamilton-Jacobi-Bellman equation can be transformed into a linear equation. The transformation is similar to the transformation used to relate the classical Hamilton-Jacobi equation to the Schrödinger equation. As a result of the linearity, the usual backward computation can be replaced by a forward diffusion process, that can be computed by stochastic integration or by the evaluation of a path integral. It is shown, how in the deterministic limit the PMP formalism is recovered. The significance of the path integral approach is that it forms the basis for a number of efficient computational methods, such as MC sampling, the Laplace approximation and the variational approximation. We show the effectiveness of the first two methods in number of examples. Examples are given that show the qualitative difference between stochastic and deterministic control and the occurrence of symmetry breaking as a function of the noise.

physics.gen-ph↗

arXiv2005

A linear theory for control of non-linear stochastic systems

We address the role of noise and the issue of efficient computation in stochastic optimal control problems. We consider a class of non-linear control problems that can be formulated as a path integral and where the noise plays the role of temperature. The path integral displays symmetry breaking and there exist a critical noise value that separates regimes where optimal control yields qualitatively different solutions. The path integral can be computed efficiently by Monte Carlo integration or by Laplace approximation, and can therefore be used to solve high dimensional stochastic control problems.

physics.comp-ph↗

arXiv2005

Effects of fast presynaptic noise in attractor neural networks

We study both analytically and numerically the effect of presynaptic noise on the transmission of information in attractor neural networks. The noise occurs on a very short-time scale compared to that for the neuron dynamics and it produces short-time synaptic depression. This is inspired in recent neurobiological findings that show that synaptic strength may either increase or decrease on a short-time scale depending on presynaptic activity. We thus describe a mechanism by which fast presynaptic noise enhances the neural network sensitivity to an external stimulus. The reason for this is that, in general, the presynaptic noise induces nonequilibrium behavior and, consequently, the space of fixed points is qualitatively modified in such a way that the system can easily scape from the attractor. As a result, the model shows, in addition to pattern recognition, class identification and categorization, which may be relevant to the understanding of some of the brain complex tasks.

q-bio.NC↗

arXiv2004

Spin-glass phase transitions on real-world graphs

We use the Bethe approximation to calculate the critical temperature for the transition from a paramagnetic to a glassy phase in spin-glass models on real-world graphs. Our criterion is based on the marginal stability of the minimum of the Bethe free energy. For uniform degree random graphs (equivalent to the Viana-Bray model) our numerical results, obtained by averaging single problem instances, are in agreement with the known critical temperature obtained by use of the replica method. Contrary to the replica method, our method immediately generalizes to arbitrary (random) graphs. We present new results for Barabasi-Albert scale-free random graphs, for which no analytical results are known. We investigate the scaling behavior of the critical temperature with graph size for both the finite and the infinite connectivity limit. We compare these with the naive Mean Field results. We observe that the Belief Propagation algorithm converges only in the paramagnetic regime.

cond-mat.stat-mech↗